Created
July 27, 2024 18:45
-
-
Save relyt0925/b7ce2a25adf83d3887c7fd81e9ac9736 to your computer and use it in GitHub Desktop.
mt_bench eval
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
[root@tyler-rhel-newimage instructlab]# /root/ilab model evaluate --benchmark mt_bench --model /var/instructlabbigdisk/instructlab/skillscheckpoints/hf_format/samples_1056/ --judge-model /var/instructlabbigdisk/instructlab/models/prometheus-eval/prometheus-8x7b-v2.0/ --base-model /var/instructlabbigdisk/instructlab/models/ibm-granite/granite-7b-base/ --output-dir /var/instructlabbigdisk/instructlab/evaltracker/skillscheckpoints/samples_1056/ --gpus 8 --backend vllm --enable-serving-output | |
INFO 2024-07-27 18:36:02,004 numexpr.utils:145: Note: detected 80 virtual cores but NumExpr set to maximum of 64, check "NUMEXPR_MAX_THREADS" environment variable. | |
INFO 2024-07-27 18:36:02,004 numexpr.utils:148: Note: NumExpr detected 80 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 16. | |
INFO 2024-07-27 18:36:02,005 numexpr.utils:161: NumExpr defaulting to 16 threads. | |
Generating answers... | |
WARNING 2024-07-27 18:36:02,158 instructlab.model.evaluate:288: Based on your hardware configuration, when using vLLM, we recommend setting max-workers between 53.0 and 160.0 for optimal performance | |
INFO 2024-07-27 18:36:02,670 instructlab.model.backends.backends:315: Trying to connect to model server at http://127.0.0.1:8000/v1 | |
INFO 2024-07-27 18:36:05,181 instructlab.model.backends.vllm:196: vLLM starting up on pid 84 at http://127.0.0.1:60583/v1 | |
INFO 2024-07-27 18:36:05,181 instructlab.model.backends.backends:328: Starting a temporary vLLM server at http://127.0.0.1:60583/v1 | |
INFO 2024-07-27 18:36:05,181 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:60583/v1, this might take a moment... Attempt: 1/80 | |
INFO 2024-07-27 18:36:09,807 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:60583/v1, this might take a moment... Attempt: 2/80 | |
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
INFO 2024-07-27 18:36:14,540 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:60583/v1, this might take a moment... Attempt: 3/80 | |
INFO 2024-07-27 18:36:19,235 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:60583/v1, this might take a moment... Attempt: 4/80 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:84:84 [0] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:84:84 [0] NCCL INFO cudaDriverVersion 12040 | |
NCCL version 2.20.5+cuda12.4 | |
tyler-rhel-newimage:113:113 [7] NCCL INFO cudaDriverVersion 12040 | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:113:113 [7] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:107:107 [1] NCCL INFO cudaDriverVersion 12040 | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:107:107 [1] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:112:112 [6] NCCL INFO cudaDriverVersion 12040 | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:112:112 [6] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:111:111 [5] NCCL INFO cudaDriverVersion 12040 | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:111:111 [5] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:110:110 [4] NCCL INFO cudaDriverVersion 12040 | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:108:108 [2] NCCL INFO cudaDriverVersion 12040 | |
tyler-rhel-newimage:110:110 [4] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:109:109 [3] NCCL INFO cudaDriverVersion 12040 | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:108:108 [2] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:109:109 [3] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:113:113 [7] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:113:113 [7] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Using network Socket | |
tyler-rhel-newimage:111:111 [5] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:111:111 [5] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Using network Socket | |
tyler-rhel-newimage:112:112 [6] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:112:112 [6] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Using network Socket | |
tyler-rhel-newimage:109:109 [3] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:84:84 [0] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:108:108 [2] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:109:109 [3] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:84:84 [0] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:108:108 [2] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Using network Socket | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Using network Socket | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Using network Socket | |
tyler-rhel-newimage:110:110 [4] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:110:110 [4] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Using network Socket | |
tyler-rhel-newimage:107:107 [1] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:107:107 [1] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Using network Socket | |
tyler-rhel-newimage:84:84 [0] NCCL INFO comm 0x56063284b3e0 rank 0 nranks 8 cudaDev 0 nvmlDev 0 busId 8010 commId 0xef46f6c69be18ced - Init START | |
tyler-rhel-newimage:108:108 [2] NCCL INFO comm 0x560632842260 rank 2 nranks 8 cudaDev 2 nvmlDev 2 busId a030 commId 0xef46f6c69be18ced - Init START | |
tyler-rhel-newimage:112:112 [6] NCCL INFO comm 0x560632844000 rank 6 nranks 8 cudaDev 6 nvmlDev 6 busId e070 commId 0xef46f6c69be18ced - Init START | |
tyler-rhel-newimage:107:107 [1] NCCL INFO comm 0x560632840d50 rank 1 nranks 8 cudaDev 1 nvmlDev 1 busId 8020 commId 0xef46f6c69be18ced - Init START | |
tyler-rhel-newimage:111:111 [5] NCCL INFO comm 0x560632845230 rank 5 nranks 8 cudaDev 5 nvmlDev 5 busId c060 commId 0xef46f6c69be18ced - Init START | |
tyler-rhel-newimage:110:110 [4] NCCL INFO comm 0x560632843570 rank 4 nranks 8 cudaDev 4 nvmlDev 4 busId c050 commId 0xef46f6c69be18ced - Init START | |
tyler-rhel-newimage:109:109 [3] NCCL INFO comm 0x560632843410 rank 3 nranks 8 cudaDev 3 nvmlDev 3 busId a040 commId 0xef46f6c69be18ced - Init START | |
tyler-rhel-newimage:113:113 [7] NCCL INFO comm 0x560632844260 rank 7 nranks 8 cudaDev 7 nvmlDev 7 busId e080 commId 0xef46f6c69be18ced - Init START | |
INFO 2024-07-27 18:36:23,942 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:60583/v1, this might take a moment... Attempt: 5/80 | |
tyler-rhel-newimage:113:113 [7] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:107:107 [1] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:84:84 [0] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:111:111 [5] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:109:109 [3] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:110:110 [4] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:108:108 [2] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Setting affinity for GPU 0 to ff,ffffffff | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Setting affinity for GPU 7 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:113:113 [7] NCCL INFO NVLS multicast support is not available on dev 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO NVLS multicast support is not available on dev 0 | |
tyler-rhel-newimage:112:112 [6] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Setting affinity for GPU 1 to ff,ffffffff | |
tyler-rhel-newimage:107:107 [1] NCCL INFO NVLS multicast support is not available on dev 1 | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Setting affinity for GPU 3 to ff,ffffffff | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Setting affinity for GPU 4 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:110:110 [4] NCCL INFO NVLS multicast support is not available on dev 4 | |
tyler-rhel-newimage:109:109 [3] NCCL INFO NVLS multicast support is not available on dev 3 | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Setting affinity for GPU 5 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:111:111 [5] NCCL INFO NVLS multicast support is not available on dev 5 | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Setting affinity for GPU 2 to ff,ffffffff | |
tyler-rhel-newimage:108:108 [2] NCCL INFO NVLS multicast support is not available on dev 2 | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Setting affinity for GPU 6 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:112:112 [6] NCCL INFO NVLS multicast support is not available on dev 6 | |
tyler-rhel-newimage:112:112 [6] NCCL INFO comm 0x560632844000 rank 6 nRanks 8 nNodes 1 localRanks 8 localRank 6 MNNVL 0 | |
tyler-rhel-newimage:113:113 [7] NCCL INFO comm 0x560632844260 rank 7 nRanks 8 nNodes 1 localRanks 8 localRank 7 MNNVL 0 | |
tyler-rhel-newimage:110:110 [4] NCCL INFO comm 0x560632843570 rank 4 nRanks 8 nNodes 1 localRanks 8 localRank 4 MNNVL 0 | |
tyler-rhel-newimage:111:111 [5] NCCL INFO comm 0x560632845230 rank 5 nRanks 8 nNodes 1 localRanks 8 localRank 5 MNNVL 0 | |
tyler-rhel-newimage:109:109 [3] NCCL INFO comm 0x560632843410 rank 3 nRanks 8 nNodes 1 localRanks 8 localRank 3 MNNVL 0 | |
tyler-rhel-newimage:108:108 [2] NCCL INFO comm 0x560632842260 rank 2 nRanks 8 nNodes 1 localRanks 8 localRank 2 MNNVL 0 | |
tyler-rhel-newimage:107:107 [1] NCCL INFO comm 0x560632840d50 rank 1 nRanks 8 nNodes 1 localRanks 8 localRank 1 MNNVL 0 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO comm 0x56063284b3e0 rank 0 nRanks 8 nNodes 1 localRanks 8 localRank 0 MNNVL 0 | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Trees [0] 7/-1/-1->6->5 [1] 7/-1/-1->6->5 [2] 7/-1/-1->6->5 [3] 7/-1/-1->6->5 [4] 7/-1/-1->6->5 [5] 7/-1/-1->6->5 [6] 7/-1/-1->6->5 [7] 7/-1/-1->6->5 [8] 7/-1/-1->6->5 [9] 7/-1/-1->6->5 [10] 7/-1/-1->6->5 [11] 7/-1/-1->6->5 [12] 7/-1/-1->6->5 [13] 7/-1/-1->6->5 [14] 7/-1/-1->6->5 [15] 7/-1/-1->6->5 [16] 7/-1/-1->6->5 [17] 7/-1/-1->6->5 [18] 7/-1/-1->6->5 [19] 7/-1/-1->6->5 [20] 7/-1/-1->6->5 [21] 7/-1/-1->6->5 [22] 7/-1/-1->6->5 [23] 7/-1/-1->6->5 | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Trees [0] 5/-1/-1->4->3 [1] 5/-1/-1->4->3 [2] 5/-1/-1->4->3 [3] 5/-1/-1->4->3 [4] 5/-1/-1->4->3 [5] 5/-1/-1->4->3 [6] 5/-1/-1->4->3 [7] 5/-1/-1->4->3 [8] 5/-1/-1->4->3 [9] 5/-1/-1->4->3 [10] 5/-1/-1->4->3 [11] 5/-1/-1->4->3 [12] 5/-1/-1->4->3 [13] 5/-1/-1->4->3 [14] 5/-1/-1->4->3 [15] 5/-1/-1->4->3 [16] 5/-1/-1->4->3 [17] 5/-1/-1->4->3 [18] 5/-1/-1->4->3 [19] 5/-1/-1->4->3 [20] 5/-1/-1->4->3 [21] 5/-1/-1->4->3 [22] 5/-1/-1->4->3 [23] 5/-1/-1->4->3 | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Trees [0] 6/-1/-1->5->4 [1] 6/-1/-1->5->4 [2] 6/-1/-1->5->4 [3] 6/-1/-1->5->4 [4] 6/-1/-1->5->4 [5] 6/-1/-1->5->4 [6] 6/-1/-1->5->4 [7] 6/-1/-1->5->4 [8] 6/-1/-1->5->4 [9] 6/-1/-1->5->4 [10] 6/-1/-1->5->4 [11] 6/-1/-1->5->4 [12] 6/-1/-1->5->4 [13] 6/-1/-1->5->4 [14] 6/-1/-1->5->4 [15] 6/-1/-1->5->4 [16] 6/-1/-1->5->4 [17] 6/-1/-1->5->4 [18] 6/-1/-1->5->4 [19] 6/-1/-1->5->4 [20] 6/-1/-1->5->4 [21] 6/-1/-1->5->4 [22] 6/-1/-1->5->4 [23] 6/-1/-1->5->4 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 00/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:110:110 [4] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:112:112 [6] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Trees [0] -1/-1/-1->7->6 [1] -1/-1/-1->7->6 [2] -1/-1/-1->7->6 [3] -1/-1/-1->7->6 [4] -1/-1/-1->7->6 [5] -1/-1/-1->7->6 [6] -1/-1/-1->7->6 [7] -1/-1/-1->7->6 [8] -1/-1/-1->7->6 [9] -1/-1/-1->7->6 [10] -1/-1/-1->7->6 [11] -1/-1/-1->7->6 [12] -1/-1/-1->7->6 [13] -1/-1/-1->7->6 [14] -1/-1/-1->7->6 [15] -1/-1/-1->7->6 [16] -1/-1/-1->7->6 [17] -1/-1/-1->7->6 [18] -1/-1/-1->7->6 [19] -1/-1/-1->7->6 [20] -1/-1/-1->7->6 [21] -1/-1/-1->7->6 [22] -1/-1/-1->7->6 [23] -1/-1/-1->7->6 | |
tyler-rhel-newimage:111:111 [5] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Trees [0] 4/-1/-1->3->2 [1] 4/-1/-1->3->2 [2] 4/-1/-1->3->2 [3] 4/-1/-1->3->2 [4] 4/-1/-1->3->2 [5] 4/-1/-1->3->2 [6] 4/-1/-1->3->2 [7] 4/-1/-1->3->2 [8] 4/-1/-1->3->2 [9] 4/-1/-1->3->2 [10] 4/-1/-1->3->2 [11] 4/-1/-1->3->2 [12] 4/-1/-1->3->2 [13] 4/-1/-1->3->2 [14] 4/-1/-1->3->2 [15] 4/-1/-1->3->2 [16] 4/-1/-1->3->2 [17] 4/-1/-1->3->2 [18] 4/-1/-1->3->2 [19] 4/-1/-1->3->2 [20] 4/-1/-1->3->2 [21] 4/-1/-1->3->2 [22] 4/-1/-1->3->2 [23] 4/-1/-1->3->2 | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Trees [0] 3/-1/-1->2->1 [1] 3/-1/-1->2->1 [2] 3/-1/-1->2->1 [3] 3/-1/-1->2->1 [4] 3/-1/-1->2->1 [5] 3/-1/-1->2->1 [6] 3/-1/-1->2->1 [7] 3/-1/-1->2->1 [8] 3/-1/-1->2->1 [9] 3/-1/-1->2->1 [10] 3/-1/-1->2->1 [11] 3/-1/-1->2->1 [12] 3/-1/-1->2->1 [13] 3/-1/-1->2->1 [14] 3/-1/-1->2->1 [15] 3/-1/-1->2->1 [16] 3/-1/-1->2->1 [17] 3/-1/-1->2->1 [18] 3/-1/-1->2->1 [19] 3/-1/-1->2->1 [20] 3/-1/-1->2->1 [21] 3/-1/-1->2->1 [22] 3/-1/-1->2->1 [23] 3/-1/-1->2->1 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 01/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Trees [0] 2/-1/-1->1->0 [1] 2/-1/-1->1->0 [2] 2/-1/-1->1->0 [3] 2/-1/-1->1->0 [4] 2/-1/-1->1->0 [5] 2/-1/-1->1->0 [6] 2/-1/-1->1->0 [7] 2/-1/-1->1->0 [8] 2/-1/-1->1->0 [9] 2/-1/-1->1->0 [10] 2/-1/-1->1->0 [11] 2/-1/-1->1->0 [12] 2/-1/-1->1->0 [13] 2/-1/-1->1->0 [14] 2/-1/-1->1->0 [15] 2/-1/-1->1->0 [16] 2/-1/-1->1->0 [17] 2/-1/-1->1->0 [18] 2/-1/-1->1->0 [19] 2/-1/-1->1->0 [20] 2/-1/-1->1->0 [21] 2/-1/-1->1->0 [22] 2/-1/-1->1->0 [23] 2/-1/-1->1->0 | |
tyler-rhel-newimage:113:113 [7] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:109:109 [3] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:108:108 [2] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 02/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:107:107 [1] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 03/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 04/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 05/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 06/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 07/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 08/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 09/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 10/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 11/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 12/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 13/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 14/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 15/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 16/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 17/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 18/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 19/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 20/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 21/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 22/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 23/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Trees [0] 1/-1/-1->0->-1 [1] 1/-1/-1->0->-1 [2] 1/-1/-1->0->-1 [3] 1/-1/-1->0->-1 [4] 1/-1/-1->0->-1 [5] 1/-1/-1->0->-1 [6] 1/-1/-1->0->-1 [7] 1/-1/-1->0->-1 [8] 1/-1/-1->0->-1 [9] 1/-1/-1->0->-1 [10] 1/-1/-1->0->-1 [11] 1/-1/-1->0->-1 [12] 1/-1/-1->0->-1 [13] 1/-1/-1->0->-1 [14] 1/-1/-1->0->-1 [15] 1/-1/-1->0->-1 [16] 1/-1/-1->0->-1 [17] 1/-1/-1->0->-1 [18] 1/-1/-1->0->-1 [19] 1/-1/-1->0->-1 [20] 1/-1/-1->0->-1 [21] 1/-1/-1->0->-1 [22] 1/-1/-1->0->-1 [23] 1/-1/-1->0->-1 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 00/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 00/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 00/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 00/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 00/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 00/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 01/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 01/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 01/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 01/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 00/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 00/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 01/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 01/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 02/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 02/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 02/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 02/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 01/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 01/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 02/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 02/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 03/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 03/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 03/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 03/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 02/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 03/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 03/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 02/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 04/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 04/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 04/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 04/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 03/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 04/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 04/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 03/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 05/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 05/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 05/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 05/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 05/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 04/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 05/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 04/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 06/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 06/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 06/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 06/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 06/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 06/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 05/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 05/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 07/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 07/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 07/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 07/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 07/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 06/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 07/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 06/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 08/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 08/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 08/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 08/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 08/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 07/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 08/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 07/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 09/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 09/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 09/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 09/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 09/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 08/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 09/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 08/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 10/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 10/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 10/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 10/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 10/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 09/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 10/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 09/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 11/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 11/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 11/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 11/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 11/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 10/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 11/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 10/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 12/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 12/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 12/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 12/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 12/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 11/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 12/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 11/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 13/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 13/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 13/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 13/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 13/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 12/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 12/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 13/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 14/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 14/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 14/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 14/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 14/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 13/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 13/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 14/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 15/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 15/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 15/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 15/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 15/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 14/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 14/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 15/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 16/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 16/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 16/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 16/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 16/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 15/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 15/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 16/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 17/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 17/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 17/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 17/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 17/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 16/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 16/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 17/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 18/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 18/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 18/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 18/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 18/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 17/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 17/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 18/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 19/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 19/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 19/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 19/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 19/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 18/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 18/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 19/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 20/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 20/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 20/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 20/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 20/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 19/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 19/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 20/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 21/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 21/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 21/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 21/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 21/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 20/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 20/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 21/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 22/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 22/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 22/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 22/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 22/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 21/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 21/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 22/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 23/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 23/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 23/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 23/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 23/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 22/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 22/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 23/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 23/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Channel 23/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Connected all rings | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Connected all rings | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Connected all rings | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Connected all rings | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Connected all rings | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Connected all rings | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Connected all rings | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Connected all rings | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 00/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 01/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 02/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 03/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 04/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 05/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 06/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 07/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 08/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 09/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 10/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 11/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 12/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 13/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 14/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 15/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 16/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 17/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 18/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 19/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 20/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 21/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 22/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Channel 23/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 00/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 00/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 00/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 00/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 00/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 00/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 01/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 01/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 01/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 01/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 01/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 01/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 02/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 02/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 02/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 02/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 02/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 02/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 03/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 03/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 03/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 03/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 03/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 03/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 04/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 04/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 04/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 04/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 04/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 04/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 05/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 05/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 05/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 05/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 05/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 05/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 06/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 06/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 06/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 06/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 06/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 06/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 07/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 07/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 07/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 07/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 07/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 07/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 08/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 08/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 08/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 08/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 08/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 08/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 09/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 09/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 09/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 09/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 09/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 09/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 10/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 10/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 10/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 10/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 10/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 10/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 11/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 11/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 11/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 11/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 11/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 11/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 12/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 12/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 12/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 12/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 12/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 12/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 13/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 13/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 13/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 13/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 13/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 14/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 14/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 14/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 14/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 14/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 15/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 15/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 15/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 15/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 15/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 16/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 16/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 16/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 16/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 13/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 16/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 17/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 17/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 17/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 17/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 14/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 17/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 18/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 18/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 18/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 18/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 15/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 18/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 19/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 19/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 19/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 19/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 16/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 19/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 20/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 20/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 20/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 20/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 17/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 20/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 21/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 21/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 21/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 21/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 18/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 21/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 22/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 22/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 22/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 22/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 19/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 22/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Channel 23/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Channel 23/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Channel 23/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Channel 23/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 20/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Channel 23/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 21/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 22/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Channel 23/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:84 [0] NCCL INFO Connected all trees | |
tyler-rhel-newimage:84:84 [0] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:84:84 [0] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:113:113 [7] NCCL INFO Connected all trees | |
tyler-rhel-newimage:113:113 [7] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:113:113 [7] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:107:107 [1] NCCL INFO Connected all trees | |
tyler-rhel-newimage:107:107 [1] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:107:107 [1] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:112:112 [6] NCCL INFO Connected all trees | |
tyler-rhel-newimage:112:112 [6] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:112:112 [6] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:108:108 [2] NCCL INFO Connected all trees | |
tyler-rhel-newimage:108:108 [2] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:108:108 [2] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:109:109 [3] NCCL INFO Connected all trees | |
tyler-rhel-newimage:109:109 [3] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:109:109 [3] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:111:111 [5] NCCL INFO Connected all trees | |
tyler-rhel-newimage:111:111 [5] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:111:111 [5] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:110:110 [4] NCCL INFO Connected all trees | |
tyler-rhel-newimage:110:110 [4] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:110:110 [4] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:84:84 [0] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:113:113 [7] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:107:107 [1] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:108:108 [2] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:112:112 [6] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:109:109 [3] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:110:110 [4] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:111:111 [5] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:112:112 [6] NCCL INFO comm 0x560632844000 rank 6 nranks 8 cudaDev 6 nvmlDev 6 busId e070 commId 0xef46f6c69be18ced - Init COMPLETE | |
tyler-rhel-newimage:110:110 [4] NCCL INFO comm 0x560632843570 rank 4 nranks 8 cudaDev 4 nvmlDev 4 busId c050 commId 0xef46f6c69be18ced - Init COMPLETE | |
tyler-rhel-newimage:111:111 [5] NCCL INFO comm 0x560632845230 rank 5 nranks 8 cudaDev 5 nvmlDev 5 busId c060 commId 0xef46f6c69be18ced - Init COMPLETE | |
tyler-rhel-newimage:113:113 [7] NCCL INFO comm 0x560632844260 rank 7 nranks 8 cudaDev 7 nvmlDev 7 busId e080 commId 0xef46f6c69be18ced - Init COMPLETE | |
tyler-rhel-newimage:107:107 [1] NCCL INFO comm 0x560632840d50 rank 1 nranks 8 cudaDev 1 nvmlDev 1 busId 8020 commId 0xef46f6c69be18ced - Init COMPLETE | |
tyler-rhel-newimage:108:108 [2] NCCL INFO comm 0x560632842260 rank 2 nranks 8 cudaDev 2 nvmlDev 2 busId a030 commId 0xef46f6c69be18ced - Init COMPLETE | |
tyler-rhel-newimage:109:109 [3] NCCL INFO comm 0x560632843410 rank 3 nranks 8 cudaDev 3 nvmlDev 3 busId a040 commId 0xef46f6c69be18ced - Init COMPLETE | |
tyler-rhel-newimage:84:84 [0] NCCL INFO comm 0x56063284b3e0 rank 0 nranks 8 cudaDev 0 nvmlDev 0 busId 8010 commId 0xef46f6c69be18ced - Init COMPLETE | |
Loading pt checkpoint shards: 0% Completed | 0/1 [00:00<?, ?it/s] | |
INFO 2024-07-27 18:36:28,309 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:60583/v1, this might take a moment... Attempt: 6/80 | |
INFO 2024-07-27 18:36:32,867 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:60583/v1, this might take a moment... Attempt: 7/80 | |
Loading pt checkpoint shards: 100% Completed | 1/1 [00:06<00:00, 6.27s/it] | |
Loading pt checkpoint shards: 100% Completed | 1/1 [00:06<00:00, 6.27s/it] | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Using network Socket | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Using network Socket | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Using network Socket | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Using network Socket | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Using network Socket | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Using network Socket | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Using network Socket | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Using network Socket | |
tyler-rhel-newimage:108:651 [2] NCCL INFO comm 0x5606496c1f20 rank 2 nranks 8 cudaDev 2 nvmlDev 2 busId a030 commId 0xb3f11bd99f7ae044 - Init START | |
tyler-rhel-newimage:107:650 [1] NCCL INFO comm 0x5606496c0b00 rank 1 nranks 8 cudaDev 1 nvmlDev 1 busId 8020 commId 0xb3f11bd99f7ae044 - Init START | |
tyler-rhel-newimage:113:648 [7] NCCL INFO comm 0x5606496ad9a0 rank 7 nranks 8 cudaDev 7 nvmlDev 7 busId e080 commId 0xb3f11bd99f7ae044 - Init START | |
tyler-rhel-newimage:111:647 [5] NCCL INFO comm 0x5606496c43b0 rank 5 nranks 8 cudaDev 5 nvmlDev 5 busId c060 commId 0xb3f11bd99f7ae044 - Init START | |
tyler-rhel-newimage:112:653 [6] NCCL INFO comm 0x5606496c38f0 rank 6 nranks 8 cudaDev 6 nvmlDev 6 busId e070 commId 0xb3f11bd99f7ae044 - Init START | |
tyler-rhel-newimage:110:649 [4] NCCL INFO comm 0x5606496c3d80 rank 4 nranks 8 cudaDev 4 nvmlDev 4 busId c050 commId 0xb3f11bd99f7ae044 - Init START | |
tyler-rhel-newimage:84:646 [0] NCCL INFO comm 0x5606496a0560 rank 0 nranks 8 cudaDev 0 nvmlDev 0 busId 8010 commId 0xb3f11bd99f7ae044 - Init START | |
tyler-rhel-newimage:109:652 [3] NCCL INFO comm 0x5606496c31a0 rank 3 nranks 8 cudaDev 3 nvmlDev 3 busId a040 commId 0xb3f11bd99f7ae044 - Init START | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Setting affinity for GPU 7 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:113:648 [7] NCCL INFO NVLS multicast support is not available on dev 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Setting affinity for GPU 0 to ff,ffffffff | |
tyler-rhel-newimage:84:646 [0] NCCL INFO NVLS multicast support is not available on dev 0 | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Setting affinity for GPU 6 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:112:653 [6] NCCL INFO NVLS multicast support is not available on dev 6 | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Setting affinity for GPU 5 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:111:647 [5] NCCL INFO NVLS multicast support is not available on dev 5 | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Setting affinity for GPU 3 to ff,ffffffff | |
tyler-rhel-newimage:109:652 [3] NCCL INFO NVLS multicast support is not available on dev 3 | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Setting affinity for GPU 2 to ff,ffffffff | |
tyler-rhel-newimage:108:651 [2] NCCL INFO NVLS multicast support is not available on dev 2 | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Setting affinity for GPU 4 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:110:649 [4] NCCL INFO NVLS multicast support is not available on dev 4 | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Setting affinity for GPU 1 to ff,ffffffff | |
tyler-rhel-newimage:107:650 [1] NCCL INFO NVLS multicast support is not available on dev 1 | |
tyler-rhel-newimage:111:647 [5] NCCL INFO comm 0x5606496c43b0 rank 5 nRanks 8 nNodes 1 localRanks 8 localRank 5 MNNVL 0 | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Trees [0] 6/-1/-1->5->4 [1] 6/-1/-1->5->4 [2] 6/-1/-1->5->4 [3] 6/-1/-1->5->4 [4] 6/-1/-1->5->4 [5] 6/-1/-1->5->4 [6] 6/-1/-1->5->4 [7] 6/-1/-1->5->4 [8] 6/-1/-1->5->4 [9] 6/-1/-1->5->4 [10] 6/-1/-1->5->4 [11] 6/-1/-1->5->4 [12] 6/-1/-1->5->4 [13] 6/-1/-1->5->4 [14] 6/-1/-1->5->4 [15] 6/-1/-1->5->4 [16] 6/-1/-1->5->4 [17] 6/-1/-1->5->4 [18] 6/-1/-1->5->4 [19] 6/-1/-1->5->4 [20] 6/-1/-1->5->4 [21] 6/-1/-1->5->4 [22] 6/-1/-1->5->4 [23] 6/-1/-1->5->4 | |
tyler-rhel-newimage:111:647 [5] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:109:652 [3] NCCL INFO comm 0x5606496c31a0 rank 3 nRanks 8 nNodes 1 localRanks 8 localRank 3 MNNVL 0 | |
tyler-rhel-newimage:108:651 [2] NCCL INFO comm 0x5606496c1f20 rank 2 nRanks 8 nNodes 1 localRanks 8 localRank 2 MNNVL 0 | |
tyler-rhel-newimage:110:649 [4] NCCL INFO comm 0x5606496c3d80 rank 4 nRanks 8 nNodes 1 localRanks 8 localRank 4 MNNVL 0 | |
tyler-rhel-newimage:113:648 [7] NCCL INFO comm 0x5606496ad9a0 rank 7 nRanks 8 nNodes 1 localRanks 8 localRank 7 MNNVL 0 | |
tyler-rhel-newimage:107:650 [1] NCCL INFO comm 0x5606496c0b00 rank 1 nRanks 8 nNodes 1 localRanks 8 localRank 1 MNNVL 0 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO comm 0x5606496a0560 rank 0 nRanks 8 nNodes 1 localRanks 8 localRank 0 MNNVL 0 | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Trees [0] 4/-1/-1->3->2 [1] 4/-1/-1->3->2 [2] 4/-1/-1->3->2 [3] 4/-1/-1->3->2 [4] 4/-1/-1->3->2 [5] 4/-1/-1->3->2 [6] 4/-1/-1->3->2 [7] 4/-1/-1->3->2 [8] 4/-1/-1->3->2 [9] 4/-1/-1->3->2 [10] 4/-1/-1->3->2 [11] 4/-1/-1->3->2 [12] 4/-1/-1->3->2 [13] 4/-1/-1->3->2 [14] 4/-1/-1->3->2 [15] 4/-1/-1->3->2 [16] 4/-1/-1->3->2 [17] 4/-1/-1->3->2 [18] 4/-1/-1->3->2 [19] 4/-1/-1->3->2 [20] 4/-1/-1->3->2 [21] 4/-1/-1->3->2 [22] 4/-1/-1->3->2 [23] 4/-1/-1->3->2 | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Trees [0] 3/-1/-1->2->1 [1] 3/-1/-1->2->1 [2] 3/-1/-1->2->1 [3] 3/-1/-1->2->1 [4] 3/-1/-1->2->1 [5] 3/-1/-1->2->1 [6] 3/-1/-1->2->1 [7] 3/-1/-1->2->1 [8] 3/-1/-1->2->1 [9] 3/-1/-1->2->1 [10] 3/-1/-1->2->1 [11] 3/-1/-1->2->1 [12] 3/-1/-1->2->1 [13] 3/-1/-1->2->1 [14] 3/-1/-1->2->1 [15] 3/-1/-1->2->1 [16] 3/-1/-1->2->1 [17] 3/-1/-1->2->1 [18] 3/-1/-1->2->1 [19] 3/-1/-1->2->1 [20] 3/-1/-1->2->1 [21] 3/-1/-1->2->1 [22] 3/-1/-1->2->1 [23] 3/-1/-1->2->1 | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Trees [0] 5/-1/-1->4->3 [1] 5/-1/-1->4->3 [2] 5/-1/-1->4->3 [3] 5/-1/-1->4->3 [4] 5/-1/-1->4->3 [5] 5/-1/-1->4->3 [6] 5/-1/-1->4->3 [7] 5/-1/-1->4->3 [8] 5/-1/-1->4->3 [9] 5/-1/-1->4->3 [10] 5/-1/-1->4->3 [11] 5/-1/-1->4->3 [12] 5/-1/-1->4->3 [13] 5/-1/-1->4->3 [14] 5/-1/-1->4->3 [15] 5/-1/-1->4->3 [16] 5/-1/-1->4->3 [17] 5/-1/-1->4->3 [18] 5/-1/-1->4->3 [19] 5/-1/-1->4->3 [20] 5/-1/-1->4->3 [21] 5/-1/-1->4->3 [22] 5/-1/-1->4->3 [23] 5/-1/-1->4->3 | |
tyler-rhel-newimage:109:652 [3] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Trees [0] -1/-1/-1->7->6 [1] -1/-1/-1->7->6 [2] -1/-1/-1->7->6 [3] -1/-1/-1->7->6 [4] -1/-1/-1->7->6 [5] -1/-1/-1->7->6 [6] -1/-1/-1->7->6 [7] -1/-1/-1->7->6 [8] -1/-1/-1->7->6 [9] -1/-1/-1->7->6 [10] -1/-1/-1->7->6 [11] -1/-1/-1->7->6 [12] -1/-1/-1->7->6 [13] -1/-1/-1->7->6 [14] -1/-1/-1->7->6 [15] -1/-1/-1->7->6 [16] -1/-1/-1->7->6 [17] -1/-1/-1->7->6 [18] -1/-1/-1->7->6 [19] -1/-1/-1->7->6 [20] -1/-1/-1->7->6 [21] -1/-1/-1->7->6 [22] -1/-1/-1->7->6 [23] -1/-1/-1->7->6 | |
tyler-rhel-newimage:108:651 [2] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Trees [0] 2/-1/-1->1->0 [1] 2/-1/-1->1->0 [2] 2/-1/-1->1->0 [3] 2/-1/-1->1->0 [4] 2/-1/-1->1->0 [5] 2/-1/-1->1->0 [6] 2/-1/-1->1->0 [7] 2/-1/-1->1->0 [8] 2/-1/-1->1->0 [9] 2/-1/-1->1->0 [10] 2/-1/-1->1->0 [11] 2/-1/-1->1->0 [12] 2/-1/-1->1->0 [13] 2/-1/-1->1->0 [14] 2/-1/-1->1->0 [15] 2/-1/-1->1->0 [16] 2/-1/-1->1->0 [17] 2/-1/-1->1->0 [18] 2/-1/-1->1->0 [19] 2/-1/-1->1->0 [20] 2/-1/-1->1->0 [21] 2/-1/-1->1->0 [22] 2/-1/-1->1->0 [23] 2/-1/-1->1->0 | |
tyler-rhel-newimage:110:649 [4] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:107:650 [1] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:113:648 [7] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 00/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:112:653 [6] NCCL INFO comm 0x5606496c38f0 rank 6 nRanks 8 nNodes 1 localRanks 8 localRank 6 MNNVL 0 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 01/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 02/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 03/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 04/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 05/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 06/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 07/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 08/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 09/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 10/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 11/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 12/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 13/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Trees [0] 7/-1/-1->6->5 [1] 7/-1/-1->6->5 [2] 7/-1/-1->6->5 [3] 7/-1/-1->6->5 [4] 7/-1/-1->6->5 [5] 7/-1/-1->6->5 [6] 7/-1/-1->6->5 [7] 7/-1/-1->6->5 [8] 7/-1/-1->6->5 [9] 7/-1/-1->6->5 [10] 7/-1/-1->6->5 [11] 7/-1/-1->6->5 [12] 7/-1/-1->6->5 [13] 7/-1/-1->6->5 [14] 7/-1/-1->6->5 [15] 7/-1/-1->6->5 [16] 7/-1/-1->6->5 [17] 7/-1/-1->6->5 [18] 7/-1/-1->6->5 [19] 7/-1/-1->6->5 [20] 7/-1/-1->6->5 [21] 7/-1/-1->6->5 [22] 7/-1/-1->6->5 [23] 7/-1/-1->6->5 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 14/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 15/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:112:653 [6] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 16/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 17/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 18/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 19/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 20/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 21/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 22/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 23/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Trees [0] 1/-1/-1->0->-1 [1] 1/-1/-1->0->-1 [2] 1/-1/-1->0->-1 [3] 1/-1/-1->0->-1 [4] 1/-1/-1->0->-1 [5] 1/-1/-1->0->-1 [6] 1/-1/-1->0->-1 [7] 1/-1/-1->0->-1 [8] 1/-1/-1->0->-1 [9] 1/-1/-1->0->-1 [10] 1/-1/-1->0->-1 [11] 1/-1/-1->0->-1 [12] 1/-1/-1->0->-1 [13] 1/-1/-1->0->-1 [14] 1/-1/-1->0->-1 [15] 1/-1/-1->0->-1 [16] 1/-1/-1->0->-1 [17] 1/-1/-1->0->-1 [18] 1/-1/-1->0->-1 [19] 1/-1/-1->0->-1 [20] 1/-1/-1->0->-1 [21] 1/-1/-1->0->-1 [22] 1/-1/-1->0->-1 [23] 1/-1/-1->0->-1 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 00/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 01/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 02/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 03/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 04/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 05/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 06/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 07/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 08/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 09/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 00/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 00/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 00/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 10/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 00/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 01/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 01/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 01/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 11/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 01/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 02/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 02/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 02/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 12/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 02/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 03/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 03/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 03/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 13/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 03/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 04/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 04/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 04/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 14/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 04/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 05/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 05/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 05/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 15/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 05/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 06/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 06/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 16/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 06/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 07/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 07/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 00/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 17/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 07/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 08/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 08/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 01/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 18/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 08/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 09/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 09/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 02/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 19/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 09/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 10/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 10/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 03/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 20/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 10/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 11/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 11/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 04/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 21/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 11/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 12/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 12/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 05/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 22/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 12/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 13/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 13/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 06/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 23/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 13/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 14/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 14/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 07/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 14/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 15/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 15/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 08/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 00/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 06/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 15/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 16/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 16/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 09/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 01/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 07/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 16/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 17/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 17/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 10/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 02/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 08/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 17/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 18/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 18/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 11/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 03/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 09/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 18/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 19/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 19/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 10/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 12/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 04/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 19/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 20/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 20/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 11/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 13/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 05/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 20/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 21/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 21/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 12/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 06/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 14/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 22/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 21/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 22/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 00/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 13/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 07/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 22/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 15/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 23/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 23/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 01/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 14/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 08/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 23/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 16/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 02/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 15/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 09/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 17/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 03/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 16/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 10/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 18/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 04/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 17/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 11/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 19/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 05/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 18/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 12/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 20/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 06/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 19/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 21/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 13/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 07/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 20/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 22/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 14/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 08/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 21/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 15/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 23/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 09/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 22/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 16/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 10/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 23/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 17/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 11/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 18/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 12/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 19/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 13/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 20/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 21/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 14/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 22/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 15/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Channel 23/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 16/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 17/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 18/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 19/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 20/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 21/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 22/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 23/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Connected all rings | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Connected all rings | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Connected all rings | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Connected all rings | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Connected all rings | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Connected all rings | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Connected all rings | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Connected all rings | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 00/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 01/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 02/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 03/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 04/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 05/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 06/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 07/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 08/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 09/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 00/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 10/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 01/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 00/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 00/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 11/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 02/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 01/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 01/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 12/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 03/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 02/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 02/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 13/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 04/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 03/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 03/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 14/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 04/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 05/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 04/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 15/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 05/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 06/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 05/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 16/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 06/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 07/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 06/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 17/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 07/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 08/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 07/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 18/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 00/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 08/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 09/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 08/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 19/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 01/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 09/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 10/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 09/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 20/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 02/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 10/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 11/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 10/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 21/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 00/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 03/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 11/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 12/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 11/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 22/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 01/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 04/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 12/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 13/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 12/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Channel 23/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 02/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 05/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 13/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 14/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 13/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 03/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 06/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 14/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 15/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 14/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 00/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 04/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 07/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 15/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 16/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 15/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 01/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 05/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 08/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 16/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 17/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 16/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 02/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 06/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 09/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 17/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 17/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 18/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 03/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 07/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 10/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 18/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 18/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 19/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 04/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 08/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 11/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 19/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 19/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 20/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 05/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 09/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 12/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 20/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 20/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 06/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 21/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 10/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 13/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 21/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 21/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 07/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 22/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 11/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 14/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 22/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 22/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 08/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Channel 23/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 12/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 15/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Channel 23/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Channel 23/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 09/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 13/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 16/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 10/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 14/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 17/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 15/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 11/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 18/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 16/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 12/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 19/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 17/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 13/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 20/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 18/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 14/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 21/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 19/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 15/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 22/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 20/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 16/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Channel 23/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 21/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 17/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 22/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 18/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Channel 23/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 19/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 20/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 21/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 22/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Channel 23/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:84:646 [0] NCCL INFO Connected all trees | |
tyler-rhel-newimage:84:646 [0] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:84:646 [0] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:107:650 [1] NCCL INFO Connected all trees | |
tyler-rhel-newimage:107:650 [1] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:107:650 [1] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:108:651 [2] NCCL INFO Connected all trees | |
tyler-rhel-newimage:111:647 [5] NCCL INFO Connected all trees | |
tyler-rhel-newimage:108:651 [2] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:111:647 [5] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:108:651 [2] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:111:647 [5] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:113:648 [7] NCCL INFO Connected all trees | |
tyler-rhel-newimage:110:649 [4] NCCL INFO Connected all trees | |
tyler-rhel-newimage:113:648 [7] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:113:648 [7] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:110:649 [4] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:112:653 [6] NCCL INFO Connected all trees | |
tyler-rhel-newimage:110:649 [4] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:109:652 [3] NCCL INFO Connected all trees | |
tyler-rhel-newimage:112:653 [6] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:112:653 [6] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:109:652 [3] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:109:652 [3] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
INFO 2024-07-27 18:36:37,726 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:60583/v1, this might take a moment... Attempt: 8/80 | |
tyler-rhel-newimage:110:649 [4] NCCL INFO comm 0x5606496c3d80 rank 4 nranks 8 cudaDev 4 nvmlDev 4 busId c050 commId 0xb3f11bd99f7ae044 - Init COMPLETE | |
tyler-rhel-newimage:108:651 [2] NCCL INFO comm 0x5606496c1f20 rank 2 nranks 8 cudaDev 2 nvmlDev 2 busId a030 commId 0xb3f11bd99f7ae044 - Init COMPLETE | |
tyler-rhel-newimage:84:646 [0] NCCL INFO comm 0x5606496a0560 rank 0 nranks 8 cudaDev 0 nvmlDev 0 busId 8010 commId 0xb3f11bd99f7ae044 - Init COMPLETE | |
tyler-rhel-newimage:107:650 [1] NCCL INFO comm 0x5606496c0b00 rank 1 nranks 8 cudaDev 1 nvmlDev 1 busId 8020 commId 0xb3f11bd99f7ae044 - Init COMPLETE | |
tyler-rhel-newimage:113:648 [7] NCCL INFO comm 0x5606496ad9a0 rank 7 nranks 8 cudaDev 7 nvmlDev 7 busId e080 commId 0xb3f11bd99f7ae044 - Init COMPLETE | |
tyler-rhel-newimage:109:652 [3] NCCL INFO comm 0x5606496c31a0 rank 3 nranks 8 cudaDev 3 nvmlDev 3 busId a040 commId 0xb3f11bd99f7ae044 - Init COMPLETE | |
tyler-rhel-newimage:111:647 [5] NCCL INFO comm 0x5606496c43b0 rank 5 nranks 8 cudaDev 5 nvmlDev 5 busId c060 commId 0xb3f11bd99f7ae044 - Init COMPLETE | |
tyler-rhel-newimage:112:653 [6] NCCL INFO comm 0x5606496c38f0 rank 6 nranks 8 cudaDev 6 nvmlDev 6 busId e070 commId 0xb3f11bd99f7ae044 - Init COMPLETE | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 00/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 00/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 00/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 01/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 00/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 00/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 02/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 01/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 01/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 01/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 03/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 00/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 01/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 02/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 02/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 02/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 04/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 03/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 01/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 02/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 03/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 03/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 05/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 04/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 04/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 02/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 04/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 03/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 05/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 06/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 00/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 05/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 05/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 03/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 04/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 06/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 07/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 06/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 01/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 06/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 05/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 04/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 07/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 08/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 07/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 02/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 07/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 05/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 08/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 09/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 06/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 08/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 03/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 08/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 09/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 10/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 06/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 07/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 09/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 04/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 09/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 10/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 11/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 08/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 07/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 10/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 10/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 05/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 11/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 12/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 09/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 08/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 11/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 11/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 12/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 06/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 13/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 10/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 12/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 09/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 07/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 12/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 13/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 14/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 11/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 13/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 10/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 13/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 08/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 14/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 15/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 12/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 14/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 11/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 14/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 09/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 15/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 16/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 13/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 15/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 10/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 15/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 12/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 16/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 17/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 14/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 16/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 16/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 11/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 18/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 17/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 13/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 15/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 17/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 17/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 12/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 19/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 18/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 14/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 16/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 18/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 18/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 20/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 13/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 19/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 19/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 15/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 19/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 17/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 20/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 14/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 21/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 20/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 20/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 16/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 18/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 21/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 15/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 22/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 21/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 21/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 17/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 19/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 22/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 23/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 16/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 22/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 22/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 18/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 23/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 20/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 24/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 17/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 23/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 23/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 24/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 19/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 25/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 21/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 18/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 24/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 24/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 25/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 20/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 26/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 22/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 19/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 25/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 25/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 26/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 27/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 26/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 26/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 27/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 28/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 27/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 27/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 28/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 29/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 28/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 28/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 29/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 30/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 29/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 29/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 30/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:110:678 [4] NCCL INFO Channel 31/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 30/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 30/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:111:680 [5] NCCL INFO Channel 31/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 21/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:109:679 [3] NCCL INFO Channel 31/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:113:681 [7] NCCL INFO Channel 31/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 22/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 23/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 23/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 20/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 24/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 24/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 21/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 25/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 25/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 22/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 26/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 26/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 23/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 27/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 24/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 27/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 28/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 25/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 28/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 29/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 26/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 29/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 30/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 27/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 30/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:108:682 [2] NCCL INFO Channel 31/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 28/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:107:683 [1] NCCL INFO Channel 31/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 29/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 30/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:112:685 [6] NCCL INFO Channel 31/1 : 6[6] -> 0[0] via P2P/IPC/read | |
INFO 2024-07-27 18:36:42,438 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:60583/v1, this might take a moment... Attempt: 9/80 | |
INFO 2024-07-27 18:36:47,110 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:60583/v1, this might take a moment... Attempt: 10/80 | |
INFO 2024-07-27 18:36:51,757 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:60583/v1, this might take a moment... Attempt: 11/80 | |
INFO 2024-07-27 18:36:56,647 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:60583/v1, this might take a moment... Attempt: 12/80 | |
embedding_mode is False. Embedding API will not work. | |
INFO: Started server process [84] | |
INFO: Waiting for application startup. | |
INFO: Application startup complete. | |
INFO: Uvicorn running on http://127.0.0.1:60583 (Press CTRL+C to quit) | |
INFO 2024-07-27 18:37:01,152 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:60583/v1, this might take a moment... Attempt: 13/80 | |
INFO: 127.0.0.1:55172 - "GET /v1/models HTTP/1.1" 200 OK | |
INFO 2024-07-27 18:37:01,164 instructlab.model.backends.backends:343: vLLM engine successfully started at http://127.0.0.1:60583/v1 | |
0%| | 0/80 [00:00<?, ?it/s]INFO: 127.0.0.1:55284 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55284 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
1%|██▌ | 1/80 [00:00<00:11, 7.12it/s]INFO: 127.0.0.1:55206 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55318 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55260 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55192 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55302 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55318 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
2%|█████ | 2/80 [00:00<00:18, 4.11it/s]INFO: 127.0.0.1:55206 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55270 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55284 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55260 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55192 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55224 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
5%|██████████ | 4/80 [00:00<00:12, 5.96it/s]INFO: 127.0.0.1:55330 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55186 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55244 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55270 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
8%|███████████████▏ | 6/80 [00:00<00:10, 7.07it/s]INFO: 127.0.0.1:55236 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55260 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55300 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55318 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55248 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55206 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55302 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55224 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55306 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55192 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
9%|█████████████████▋ | 7/80 [00:01<00:11, 6.10it/s]INFO: 127.0.0.1:55284 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55212 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55260 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
12%|█████████████████████████▏ | 10/80 [00:01<00:07, 9.80it/s]INFO: 127.0.0.1:55260 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55302 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55270 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55306 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55186 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55260 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
15%|██████████████████████████████▏ | 12/80 [00:01<00:08, 8.21it/s]INFO: 127.0.0.1:55302 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55212 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55270 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
19%|█████████████████████████████████████▋ | 15/80 [00:01<00:05, 11.38it/s]INFO: 127.0.0.1:55284 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55206 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55306 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55186 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55302 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55318 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
24%|███████████████████████████████████████████████▋ | 19/80 [00:01<00:04, 14.91it/s]INFO: 127.0.0.1:55300 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55248 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55244 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
28%|███████████████████████████████████████████████████████▎ | 22/80 [00:02<00:03, 16.92it/s]INFO: 127.0.0.1:55260 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55236 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55302 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
30%|████████████████████████████████████████████████████████████▎ | 24/80 [00:02<00:03, 17.46it/s]INFO: 127.0.0.1:55206 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55244 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55260 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55224 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55302 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55330 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55306 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55300 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55236 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
32%|█████████████████████████████████████████████████████████████████▎ | 26/80 [00:02<00:04, 12.88it/s]INFO: 127.0.0.1:55248 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55186 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55192 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
35%|██████████████████████████████████████████████████████████████████████▎ | 28/80 [00:02<00:03, 13.26it/s]INFO: 127.0.0.1:55212 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55302 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55206 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55318 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55244 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
39%|█████████████████████████████████████████████████████████████████████████████▉ | 31/80 [00:02<00:03, 14.51it/s]INFO: 127.0.0.1:55236 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55330 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55260 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55300 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
41%|██████████████████████████████████████████████████████████████████████████████████▉ | 33/80 [00:02<00:03, 12.59it/s]INFO: 127.0.0.1:55248 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55192 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55306 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
44%|███████████████████████████████████████████████████████████████████████████████████████▉ | 35/80 [00:03<00:03, 13.67it/s]INFO: 127.0.0.1:55318 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55192 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55302 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55330 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
48%|███████████████████████████████████████████████████████████████████████████████████████████████▍ | 38/80 [00:03<00:02, 15.58it/s]INFO: 127.0.0.1:55284 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55212 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55236 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55260 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55248 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55186 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55270 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55224 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
51%|███████████████████████████████████████████████████████████████████████████████████████████████████████ | 41/80 [00:03<00:02, 14.88it/s]INFO: 127.0.0.1:55212 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55302 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
54%|████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 43/80 [00:03<00:02, 14.09it/s]INFO: 127.0.0.1:55330 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55206 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55236 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55244 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55306 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55224 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55302 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55318 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55330 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
56%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 45/80 [00:03<00:03, 9.43it/s]INFO: 127.0.0.1:55224 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55186 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
59%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 47/80 [00:04<00:03, 10.38it/s]INFO: 127.0.0.1:55206 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55302 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55236 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55248 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55284 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
62%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 50/80 [00:04<00:02, 10.79it/s]INFO: 127.0.0.1:55212 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55330 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55244 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55306 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
65%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 52/80 [00:04<00:02, 9.75it/s]INFO: 127.0.0.1:55248 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55300 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55192 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55302 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55236 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
68%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 54/80 [00:04<00:02, 9.03it/s]INFO: 127.0.0.1:55318 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55284 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55300 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
70%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 56/80 [00:05<00:02, 9.97it/s]INFO: 127.0.0.1:55248 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55330 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55192 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55212 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
74%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ | 59/80 [00:05<00:01, 13.11it/s]INFO: 127.0.0.1:55206 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55244 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55306 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55224 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55284 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55212 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55248 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
76%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 61/80 [00:05<00:01, 11.74it/s]INFO: 127.0.0.1:55302 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55318 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55192 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55306 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
79%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 63/80 [00:05<00:01, 11.35it/s]INFO: 127.0.0.1:55330 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55212 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55270 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
81%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 65/80 [00:05<00:01, 12.17it/s]INFO: 127.0.0.1:55300 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55192 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55306 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55244 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
84%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 67/80 [00:05<00:01, 11.98it/s]INFO: 127.0.0.1:55318 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55224 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55300 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
86%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 69/80 [00:06<00:00, 12.75it/s]INFO: 127.0.0.1:55330 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55236 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55302 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55186 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55206 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
90%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 72/80 [00:06<00:00, 13.05it/s]INFO: 127.0.0.1:55248 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55192 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55236 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
92%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 74/80 [00:06<00:00, 8.86it/s]INFO: 127.0.0.1:55284 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55212 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55260 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55224 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55212 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
95%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 76/80 [00:07<00:00, 7.59it/s]INFO: 127.0.0.1:55192 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55236 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
98%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 78/80 [00:07<00:00, 8.83it/s]INFO: 127.0.0.1:55206 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:55186 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 80/80 [00:12<00:00, 6.19it/s] | |
INFO: Shutting down | |
INFO: Waiting for application shutdown. | |
INFO: Application shutdown complete. | |
INFO: Finished server process [84] | |
[rank0]:[W CudaIPCTypes.cpp:16] Producer process has been terminated before all shared CUDA tensors released. See Note [Sharing CUDA tensors] | |
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 1 leaked shared_memory objects to clean up at shutdown | |
warnings.warn('resource_tracker: There appear to be %d ' | |
Evaluating answers... | |
WARNING 2024-07-27 18:37:26,124 instructlab.model.evaluate:288: Based on your hardware configuration, when using vLLM, we recommend setting max-workers between 53.0 and 160.0 for optimal performance | |
INFO 2024-07-27 18:37:26,189 instructlab.model.backends.backends:315: Trying to connect to model server at http://127.0.0.1:8000/v1 | |
INFO 2024-07-27 18:37:28,923 instructlab.model.backends.vllm:196: vLLM starting up on pid 801 at http://127.0.0.1:59587/v1 | |
INFO 2024-07-27 18:37:28,923 instructlab.model.backends.backends:328: Starting a temporary vLLM server at http://127.0.0.1:59587/v1 | |
INFO 2024-07-27 18:37:28,923 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 1/80 | |
INFO 2024-07-27 18:37:33,466 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 2/80 | |
INFO 2024-07-27 18:37:38,160 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 3/80 | |
INFO 2024-07-27 18:37:42,743 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 4/80 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:801:801 [0] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:801:801 [0] NCCL INFO cudaDriverVersion 12040 | |
NCCL version 2.20.5+cuda12.4 | |
tyler-rhel-newimage:827:827 [4] NCCL INFO cudaDriverVersion 12040 | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:827:827 [4] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:830:830 [7] NCCL INFO cudaDriverVersion 12040 | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:830:830 [7] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:828:828 [5] NCCL INFO cudaDriverVersion 12040 | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:828:828 [5] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:825:825 [2] NCCL INFO cudaDriverVersion 12040 | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:825:825 [2] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:824:824 [1] NCCL INFO cudaDriverVersion 12040 | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:824:824 [1] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:829:829 [6] NCCL INFO cudaDriverVersion 12040 | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:826:826 [3] NCCL INFO cudaDriverVersion 12040 | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Bootstrap : Using enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:829:829 [6] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:826:826 [3] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation | |
tyler-rhel-newimage:801:801 [0] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:801:801 [0] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Using network Socket | |
tyler-rhel-newimage:827:827 [4] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:827:827 [4] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Using network Socket | |
tyler-rhel-newimage:830:830 [7] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:830:830 [7] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Using network Socket | |
tyler-rhel-newimage:825:825 [2] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:825:825 [2] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Using network Socket | |
tyler-rhel-newimage:826:826 [3] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:826:826 [3] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Using network Socket | |
tyler-rhel-newimage:824:824 [1] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:824:824 [1] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Using network Socket | |
INFO 2024-07-27 18:37:47,235 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 5/80 | |
tyler-rhel-newimage:828:828 [5] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:828:828 [5] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Using network Socket | |
tyler-rhel-newimage:829:829 [6] NCCL INFO NET/IB : No device found. | |
tyler-rhel-newimage:829:829 [6] NCCL INFO NET/Socket : Using [0]enp8s0:192.168.48.11<0> | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Using network Socket | |
tyler-rhel-newimage:828:828 [5] NCCL INFO comm 0x555b94f76f30 rank 5 nranks 8 cudaDev 5 nvmlDev 5 busId c060 commId 0xc1aaaefa85b64c46 - Init START | |
tyler-rhel-newimage:825:825 [2] NCCL INFO comm 0x555b94f76350 rank 2 nranks 8 cudaDev 2 nvmlDev 2 busId a030 commId 0xc1aaaefa85b64c46 - Init START | |
tyler-rhel-newimage:829:829 [6] NCCL INFO comm 0x555b94f77fe0 rank 6 nranks 8 cudaDev 6 nvmlDev 6 busId e070 commId 0xc1aaaefa85b64c46 - Init START | |
tyler-rhel-newimage:801:801 [0] NCCL INFO comm 0x555b94f7de20 rank 0 nranks 8 cudaDev 0 nvmlDev 0 busId 8010 commId 0xc1aaaefa85b64c46 - Init START | |
tyler-rhel-newimage:824:824 [1] NCCL INFO comm 0x555b94f76110 rank 1 nranks 8 cudaDev 1 nvmlDev 1 busId 8020 commId 0xc1aaaefa85b64c46 - Init START | |
tyler-rhel-newimage:827:827 [4] NCCL INFO comm 0x555b94f76b60 rank 4 nranks 8 cudaDev 4 nvmlDev 4 busId c050 commId 0xc1aaaefa85b64c46 - Init START | |
tyler-rhel-newimage:830:830 [7] NCCL INFO comm 0x555b94f79470 rank 7 nranks 8 cudaDev 7 nvmlDev 7 busId e080 commId 0xc1aaaefa85b64c46 - Init START | |
tyler-rhel-newimage:826:826 [3] NCCL INFO comm 0x555b94f76680 rank 3 nranks 8 cudaDev 3 nvmlDev 3 busId a040 commId 0xc1aaaefa85b64c46 - Init START | |
tyler-rhel-newimage:828:828 [5] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:824:824 [1] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:829:829 [6] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:825:825 [2] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:801:801 [0] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:827:827 [4] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:830:830 [7] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Setting affinity for GPU 5 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:828:828 [5] NCCL INFO NVLS multicast support is not available on dev 5 | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Setting affinity for GPU 6 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:829:829 [6] NCCL INFO NVLS multicast support is not available on dev 6 | |
tyler-rhel-newimage:826:826 [3] NCCL INFO NCCL_CUMEM_ENABLE set by environment to 0. | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Setting affinity for GPU 0 to ff,ffffffff | |
tyler-rhel-newimage:801:801 [0] NCCL INFO NVLS multicast support is not available on dev 0 | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Setting affinity for GPU 2 to ff,ffffffff | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Setting affinity for GPU 1 to ff,ffffffff | |
tyler-rhel-newimage:824:824 [1] NCCL INFO NVLS multicast support is not available on dev 1 | |
tyler-rhel-newimage:825:825 [2] NCCL INFO NVLS multicast support is not available on dev 2 | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Setting affinity for GPU 4 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:827:827 [4] NCCL INFO NVLS multicast support is not available on dev 4 | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Setting affinity for GPU 7 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:830:830 [7] NCCL INFO NVLS multicast support is not available on dev 7 | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Setting affinity for GPU 3 to ff,ffffffff | |
tyler-rhel-newimage:826:826 [3] NCCL INFO NVLS multicast support is not available on dev 3 | |
tyler-rhel-newimage:826:826 [3] NCCL INFO comm 0x555b94f76680 rank 3 nRanks 8 nNodes 1 localRanks 8 localRank 3 MNNVL 0 | |
tyler-rhel-newimage:825:825 [2] NCCL INFO comm 0x555b94f76350 rank 2 nRanks 8 nNodes 1 localRanks 8 localRank 2 MNNVL 0 | |
tyler-rhel-newimage:824:824 [1] NCCL INFO comm 0x555b94f76110 rank 1 nRanks 8 nNodes 1 localRanks 8 localRank 1 MNNVL 0 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO comm 0x555b94f7de20 rank 0 nRanks 8 nNodes 1 localRanks 8 localRank 0 MNNVL 0 | |
tyler-rhel-newimage:830:830 [7] NCCL INFO comm 0x555b94f79470 rank 7 nRanks 8 nNodes 1 localRanks 8 localRank 7 MNNVL 0 | |
tyler-rhel-newimage:827:827 [4] NCCL INFO comm 0x555b94f76b60 rank 4 nRanks 8 nNodes 1 localRanks 8 localRank 4 MNNVL 0 | |
tyler-rhel-newimage:829:829 [6] NCCL INFO comm 0x555b94f77fe0 rank 6 nRanks 8 nNodes 1 localRanks 8 localRank 6 MNNVL 0 | |
tyler-rhel-newimage:828:828 [5] NCCL INFO comm 0x555b94f76f30 rank 5 nRanks 8 nNodes 1 localRanks 8 localRank 5 MNNVL 0 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 00/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 01/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 02/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Trees [0] 3/-1/-1->2->1 [1] 3/-1/-1->2->1 [2] 3/-1/-1->2->1 [3] 3/-1/-1->2->1 [4] 3/-1/-1->2->1 [5] 3/-1/-1->2->1 [6] 3/-1/-1->2->1 [7] 3/-1/-1->2->1 [8] 3/-1/-1->2->1 [9] 3/-1/-1->2->1 [10] 3/-1/-1->2->1 [11] 3/-1/-1->2->1 [12] 3/-1/-1->2->1 [13] 3/-1/-1->2->1 [14] 3/-1/-1->2->1 [15] 3/-1/-1->2->1 [16] 3/-1/-1->2->1 [17] 3/-1/-1->2->1 [18] 3/-1/-1->2->1 [19] 3/-1/-1->2->1 [20] 3/-1/-1->2->1 [21] 3/-1/-1->2->1 [22] 3/-1/-1->2->1 [23] 3/-1/-1->2->1 | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Trees [0] 4/-1/-1->3->2 [1] 4/-1/-1->3->2 [2] 4/-1/-1->3->2 [3] 4/-1/-1->3->2 [4] 4/-1/-1->3->2 [5] 4/-1/-1->3->2 [6] 4/-1/-1->3->2 [7] 4/-1/-1->3->2 [8] 4/-1/-1->3->2 [9] 4/-1/-1->3->2 [10] 4/-1/-1->3->2 [11] 4/-1/-1->3->2 [12] 4/-1/-1->3->2 [13] 4/-1/-1->3->2 [14] 4/-1/-1->3->2 [15] 4/-1/-1->3->2 [16] 4/-1/-1->3->2 [17] 4/-1/-1->3->2 [18] 4/-1/-1->3->2 [19] 4/-1/-1->3->2 [20] 4/-1/-1->3->2 [21] 4/-1/-1->3->2 [22] 4/-1/-1->3->2 [23] 4/-1/-1->3->2 | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Trees [0] 2/-1/-1->1->0 [1] 2/-1/-1->1->0 [2] 2/-1/-1->1->0 [3] 2/-1/-1->1->0 [4] 2/-1/-1->1->0 [5] 2/-1/-1->1->0 [6] 2/-1/-1->1->0 [7] 2/-1/-1->1->0 [8] 2/-1/-1->1->0 [9] 2/-1/-1->1->0 [10] 2/-1/-1->1->0 [11] 2/-1/-1->1->0 [12] 2/-1/-1->1->0 [13] 2/-1/-1->1->0 [14] 2/-1/-1->1->0 [15] 2/-1/-1->1->0 [16] 2/-1/-1->1->0 [17] 2/-1/-1->1->0 [18] 2/-1/-1->1->0 [19] 2/-1/-1->1->0 [20] 2/-1/-1->1->0 [21] 2/-1/-1->1->0 [22] 2/-1/-1->1->0 [23] 2/-1/-1->1->0 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 03/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Trees [0] -1/-1/-1->7->6 [1] -1/-1/-1->7->6 [2] -1/-1/-1->7->6 [3] -1/-1/-1->7->6 [4] -1/-1/-1->7->6 [5] -1/-1/-1->7->6 [6] -1/-1/-1->7->6 [7] -1/-1/-1->7->6 [8] -1/-1/-1->7->6 [9] -1/-1/-1->7->6 [10] -1/-1/-1->7->6 [11] -1/-1/-1->7->6 [12] -1/-1/-1->7->6 [13] -1/-1/-1->7->6 [14] -1/-1/-1->7->6 [15] -1/-1/-1->7->6 [16] -1/-1/-1->7->6 [17] -1/-1/-1->7->6 [18] -1/-1/-1->7->6 [19] -1/-1/-1->7->6 [20] -1/-1/-1->7->6 [21] -1/-1/-1->7->6 [22] -1/-1/-1->7->6 [23] -1/-1/-1->7->6 | |
tyler-rhel-newimage:825:825 [2] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:826:826 [3] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:824:824 [1] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 04/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Trees [0] 5/-1/-1->4->3 [1] 5/-1/-1->4->3 [2] 5/-1/-1->4->3 [3] 5/-1/-1->4->3 [4] 5/-1/-1->4->3 [5] 5/-1/-1->4->3 [6] 5/-1/-1->4->3 [7] 5/-1/-1->4->3 [8] 5/-1/-1->4->3 [9] 5/-1/-1->4->3 [10] 5/-1/-1->4->3 [11] 5/-1/-1->4->3 [12] 5/-1/-1->4->3 [13] 5/-1/-1->4->3 [14] 5/-1/-1->4->3 [15] 5/-1/-1->4->3 [16] 5/-1/-1->4->3 [17] 5/-1/-1->4->3 [18] 5/-1/-1->4->3 [19] 5/-1/-1->4->3 [20] 5/-1/-1->4->3 [21] 5/-1/-1->4->3 [22] 5/-1/-1->4->3 [23] 5/-1/-1->4->3 | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Trees [0] 7/-1/-1->6->5 [1] 7/-1/-1->6->5 [2] 7/-1/-1->6->5 [3] 7/-1/-1->6->5 [4] 7/-1/-1->6->5 [5] 7/-1/-1->6->5 [6] 7/-1/-1->6->5 [7] 7/-1/-1->6->5 [8] 7/-1/-1->6->5 [9] 7/-1/-1->6->5 [10] 7/-1/-1->6->5 [11] 7/-1/-1->6->5 [12] 7/-1/-1->6->5 [13] 7/-1/-1->6->5 [14] 7/-1/-1->6->5 [15] 7/-1/-1->6->5 [16] 7/-1/-1->6->5 [17] 7/-1/-1->6->5 [18] 7/-1/-1->6->5 [19] 7/-1/-1->6->5 [20] 7/-1/-1->6->5 [21] 7/-1/-1->6->5 [22] 7/-1/-1->6->5 [23] 7/-1/-1->6->5 | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Trees [0] 6/-1/-1->5->4 [1] 6/-1/-1->5->4 [2] 6/-1/-1->5->4 [3] 6/-1/-1->5->4 [4] 6/-1/-1->5->4 [5] 6/-1/-1->5->4 [6] 6/-1/-1->5->4 [7] 6/-1/-1->5->4 [8] 6/-1/-1->5->4 [9] 6/-1/-1->5->4 [10] 6/-1/-1->5->4 [11] 6/-1/-1->5->4 [12] 6/-1/-1->5->4 [13] 6/-1/-1->5->4 [14] 6/-1/-1->5->4 [15] 6/-1/-1->5->4 [16] 6/-1/-1->5->4 [17] 6/-1/-1->5->4 [18] 6/-1/-1->5->4 [19] 6/-1/-1->5->4 [20] 6/-1/-1->5->4 [21] 6/-1/-1->5->4 [22] 6/-1/-1->5->4 [23] 6/-1/-1->5->4 | |
tyler-rhel-newimage:829:829 [6] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:830:830 [7] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 05/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:827:827 [4] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:828:828 [5] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 06/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 07/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 08/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 09/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 10/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 11/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 12/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 13/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 14/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 15/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 16/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 17/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 18/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 19/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 20/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 21/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 22/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 23/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Trees [0] 1/-1/-1->0->-1 [1] 1/-1/-1->0->-1 [2] 1/-1/-1->0->-1 [3] 1/-1/-1->0->-1 [4] 1/-1/-1->0->-1 [5] 1/-1/-1->0->-1 [6] 1/-1/-1->0->-1 [7] 1/-1/-1->0->-1 [8] 1/-1/-1->0->-1 [9] 1/-1/-1->0->-1 [10] 1/-1/-1->0->-1 [11] 1/-1/-1->0->-1 [12] 1/-1/-1->0->-1 [13] 1/-1/-1->0->-1 [14] 1/-1/-1->0->-1 [15] 1/-1/-1->0->-1 [16] 1/-1/-1->0->-1 [17] 1/-1/-1->0->-1 [18] 1/-1/-1->0->-1 [19] 1/-1/-1->0->-1 [20] 1/-1/-1->0->-1 [21] 1/-1/-1->0->-1 [22] 1/-1/-1->0->-1 [23] 1/-1/-1->0->-1 | |
tyler-rhel-newimage:801:801 [0] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 00/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 00/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 01/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 00/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 00/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 01/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 02/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 01/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 01/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 02/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 00/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 03/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 02/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 02/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 03/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 01/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 04/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 03/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 03/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 04/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 02/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 05/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 04/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 04/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 05/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 03/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 06/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 05/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 05/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 06/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 04/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 07/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 06/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 06/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 07/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 00/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 05/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 08/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 07/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 07/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 01/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 08/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 06/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 09/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 08/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 08/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 02/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 09/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 07/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 10/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 09/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 09/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 00/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 10/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 00/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 03/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 08/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 11/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 10/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 10/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 01/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 11/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 01/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 04/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 09/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 12/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 11/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 11/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 02/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 12/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 02/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 05/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 10/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 13/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 12/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 12/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 03/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 13/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 03/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 06/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 13/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 11/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 14/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 13/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 04/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 14/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 04/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 07/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 14/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 12/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 15/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 14/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 05/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 15/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 05/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 08/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 15/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 13/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 16/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 15/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 06/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 16/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 06/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 09/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 17/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 16/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 14/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 16/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 07/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 17/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 07/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 10/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 17/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 18/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 15/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 17/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 08/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 18/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 08/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 11/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 18/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 19/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 16/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 18/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 09/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 09/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 19/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 12/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 19/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 20/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 17/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 19/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 10/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 10/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 20/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 18/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 20/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 21/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 13/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 20/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 11/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 11/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 21/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 19/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 21/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 22/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 14/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 21/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 12/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 12/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 22/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 20/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 22/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 23/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 15/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 22/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 13/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 13/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 23/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 21/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Channel 23/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 16/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 23/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 14/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 14/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 22/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 17/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 15/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 15/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 23/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 18/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 16/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 16/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 19/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 17/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 17/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 20/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 18/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 18/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 21/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 19/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 19/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 22/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 20/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 20/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 23/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 21/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 21/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 22/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 22/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 23/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 23/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Connected all rings | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 00/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 01/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Connected all rings | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Connected all rings | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 02/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 03/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 04/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Connected all rings | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Connected all rings | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Connected all rings | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 05/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Connected all rings | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Connected all rings | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 06/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 07/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 08/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 09/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 10/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 11/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 12/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 13/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 14/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 15/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 16/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 17/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 18/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 19/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 20/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 21/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 22/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Channel 23/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 00/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 00/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 01/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 01/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 02/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 02/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 03/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 00/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 00/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 00/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 03/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 04/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 01/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 01/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 01/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 04/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 00/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 05/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 02/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 02/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 02/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 05/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 01/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 06/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 03/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 03/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 03/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 06/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 02/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 07/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 04/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 04/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 04/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 07/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 03/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 08/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 05/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 08/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 05/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 05/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 04/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 09/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 06/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 09/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 06/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 06/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 05/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 10/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 07/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 10/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 07/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 07/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 06/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 11/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 08/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 11/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 08/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 08/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 12/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 09/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 12/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 09/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 09/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 10/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 13/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 13/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 10/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 10/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 07/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 11/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 14/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 14/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 11/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 11/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 12/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 08/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 15/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 15/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 12/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 12/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 13/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 09/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 16/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 16/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 13/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 13/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 14/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 10/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 17/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 17/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 14/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 14/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 15/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 11/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 18/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 18/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 15/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 15/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 16/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 12/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 19/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 19/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 16/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 16/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 17/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 13/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 20/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 20/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 17/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 18/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 17/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 14/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 21/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 21/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 18/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 19/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 18/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 15/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 22/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 19/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 22/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 20/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 19/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 16/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Channel 23/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 20/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Channel 23/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 21/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 20/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 17/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 21/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 22/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 21/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 18/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 22/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Channel 23/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 19/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 22/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Channel 23/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 20/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Channel 23/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 21/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 22/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Channel 23/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:830:830 [7] NCCL INFO Connected all trees | |
tyler-rhel-newimage:830:830 [7] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:830:830 [7] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:829:829 [6] NCCL INFO Connected all trees | |
tyler-rhel-newimage:829:829 [6] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:829:829 [6] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:801:801 [0] NCCL INFO Connected all trees | |
tyler-rhel-newimage:825:825 [2] NCCL INFO Connected all trees | |
tyler-rhel-newimage:801:801 [0] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:824:824 [1] NCCL INFO Connected all trees | |
tyler-rhel-newimage:801:801 [0] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:825:825 [2] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:824:824 [1] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:825:825 [2] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:824:824 [1] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:826:826 [3] NCCL INFO Connected all trees | |
tyler-rhel-newimage:826:826 [3] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:826:826 [3] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:828:828 [5] NCCL INFO Connected all trees | |
tyler-rhel-newimage:827:827 [4] NCCL INFO Connected all trees | |
tyler-rhel-newimage:828:828 [5] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:828:828 [5] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:827:827 [4] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:827:827 [4] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:830:830 [7] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:829:829 [6] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:801:801 [0] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:825:825 [2] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:824:824 [1] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:826:826 [3] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:827:827 [4] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:828:828 [5] NCCL INFO NCCL_WORK_FIFO_DEPTH set by environment to 4194304. | |
tyler-rhel-newimage:829:829 [6] NCCL INFO comm 0x555b94f77fe0 rank 6 nranks 8 cudaDev 6 nvmlDev 6 busId e070 commId 0xc1aaaefa85b64c46 - Init COMPLETE | |
tyler-rhel-newimage:827:827 [4] NCCL INFO comm 0x555b94f76b60 rank 4 nranks 8 cudaDev 4 nvmlDev 4 busId c050 commId 0xc1aaaefa85b64c46 - Init COMPLETE | |
tyler-rhel-newimage:830:830 [7] NCCL INFO comm 0x555b94f79470 rank 7 nranks 8 cudaDev 7 nvmlDev 7 busId e080 commId 0xc1aaaefa85b64c46 - Init COMPLETE | |
tyler-rhel-newimage:824:824 [1] NCCL INFO comm 0x555b94f76110 rank 1 nranks 8 cudaDev 1 nvmlDev 1 busId 8020 commId 0xc1aaaefa85b64c46 - Init COMPLETE | |
tyler-rhel-newimage:828:828 [5] NCCL INFO comm 0x555b94f76f30 rank 5 nranks 8 cudaDev 5 nvmlDev 5 busId c060 commId 0xc1aaaefa85b64c46 - Init COMPLETE | |
tyler-rhel-newimage:826:826 [3] NCCL INFO comm 0x555b94f76680 rank 3 nranks 8 cudaDev 3 nvmlDev 3 busId a040 commId 0xc1aaaefa85b64c46 - Init COMPLETE | |
tyler-rhel-newimage:825:825 [2] NCCL INFO comm 0x555b94f76350 rank 2 nranks 8 cudaDev 2 nvmlDev 2 busId a030 commId 0xc1aaaefa85b64c46 - Init COMPLETE | |
tyler-rhel-newimage:801:801 [0] NCCL INFO comm 0x555b94f7de20 rank 0 nranks 8 cudaDev 0 nvmlDev 0 busId 8010 commId 0xc1aaaefa85b64c46 - Init COMPLETE | |
Loading safetensors checkpoint shards: 0% Completed | 0/19 [00:00<?, ?it/s] | |
Loading safetensors checkpoint shards: 5% Completed | 1/19 [00:00<00:05, 3.02it/s] | |
INFO 2024-07-27 18:37:52,083 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 6/80 | |
Loading safetensors checkpoint shards: 11% Completed | 2/19 [00:00<00:05, 2.95it/s] | |
Loading safetensors checkpoint shards: 16% Completed | 3/19 [00:00<00:05, 3.07it/s] | |
Loading safetensors checkpoint shards: 21% Completed | 4/19 [00:01<00:05, 2.98it/s] | |
Loading safetensors checkpoint shards: 26% Completed | 5/19 [00:01<00:04, 3.04it/s] | |
Loading safetensors checkpoint shards: 32% Completed | 6/19 [00:02<00:04, 2.95it/s] | |
Loading safetensors checkpoint shards: 37% Completed | 7/19 [00:02<00:04, 2.94it/s] | |
Loading safetensors checkpoint shards: 42% Completed | 8/19 [00:02<00:03, 2.91it/s] | |
Loading safetensors checkpoint shards: 47% Completed | 9/19 [00:03<00:03, 2.88it/s] | |
Loading safetensors checkpoint shards: 53% Completed | 10/19 [00:03<00:03, 2.84it/s] | |
Loading safetensors checkpoint shards: 58% Completed | 11/19 [00:03<00:02, 2.78it/s] | |
Loading safetensors checkpoint shards: 63% Completed | 12/19 [00:04<00:02, 2.81it/s] | |
Loading safetensors checkpoint shards: 68% Completed | 13/19 [00:04<00:02, 2.85it/s] | |
Loading safetensors checkpoint shards: 74% Completed | 14/19 [00:04<00:01, 2.87it/s] | |
INFO 2024-07-27 18:37:56,538 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 7/80 | |
Loading safetensors checkpoint shards: 79% Completed | 15/19 [00:05<00:01, 2.93it/s] | |
Loading safetensors checkpoint shards: 84% Completed | 16/19 [00:05<00:01, 2.94it/s] | |
Loading safetensors checkpoint shards: 89% Completed | 17/19 [00:05<00:00, 3.08it/s] | |
Loading safetensors checkpoint shards: 95% Completed | 18/19 [00:06<00:00, 3.09it/s] | |
Loading safetensors checkpoint shards: 100% Completed | 19/19 [00:06<00:00, 3.42it/s] | |
Loading safetensors checkpoint shards: 100% Completed | 19/19 [00:06<00:00, 3.00it/s] | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Using network Socket | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Using network Socket | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Using network Socket | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Using network Socket | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Using network Socket | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Using network Socket | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Using network Socket | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Using non-device net plugin version 0 | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Using network Socket | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO comm 0x555ba0549a40 rank 3 nranks 8 cudaDev 3 nvmlDev 3 busId a040 commId 0xd56327a586613906 - Init START | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO comm 0x555ba114a940 rank 6 nranks 8 cudaDev 6 nvmlDev 6 busId e070 commId 0xd56327a586613906 - Init START | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO comm 0x555b9f749530 rank 4 nranks 8 cudaDev 4 nvmlDev 4 busId c050 commId 0xd56327a586613906 - Init START | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO comm 0x555ba0547ff0 rank 2 nranks 8 cudaDev 2 nvmlDev 2 busId a030 commId 0xd56327a586613906 - Init START | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO comm 0x555bab11e710 rank 0 nranks 8 cudaDev 0 nvmlDev 0 busId 8010 commId 0xd56327a586613906 - Init START | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO comm 0x555b9f748ea0 rank 1 nranks 8 cudaDev 1 nvmlDev 1 busId 8020 commId 0xd56327a586613906 - Init START | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO comm 0x555ba0534fd0 rank 7 nranks 8 cudaDev 7 nvmlDev 7 busId e080 commId 0xd56327a586613906 - Init START | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO comm 0x555b9f749730 rank 5 nranks 8 cudaDev 5 nvmlDev 5 busId c060 commId 0xd56327a586613906 - Init START | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Setting affinity for GPU 3 to ff,ffffffff | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO NVLS multicast support is not available on dev 3 | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Setting affinity for GPU 6 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO NVLS multicast support is not available on dev 6 | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Setting affinity for GPU 1 to ff,ffffffff | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO NVLS multicast support is not available on dev 1 | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Setting affinity for GPU 5 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO NVLS multicast support is not available on dev 5 | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Setting affinity for GPU 4 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO NVLS multicast support is not available on dev 4 | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Setting affinity for GPU 7 to ffff,ffffff00,00000000 | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO NVLS multicast support is not available on dev 7 | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Setting affinity for GPU 2 to ff,ffffffff | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO NVLS multicast support is not available on dev 2 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Setting affinity for GPU 0 to ff,ffffffff | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO NVLS multicast support is not available on dev 0 | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO comm 0x555b9f749530 rank 4 nRanks 8 nNodes 1 localRanks 8 localRank 4 MNNVL 0 | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Trees [0] 5/-1/-1->4->3 [1] 5/-1/-1->4->3 [2] 5/-1/-1->4->3 [3] 5/-1/-1->4->3 [4] 5/-1/-1->4->3 [5] 5/-1/-1->4->3 [6] 5/-1/-1->4->3 [7] 5/-1/-1->4->3 [8] 5/-1/-1->4->3 [9] 5/-1/-1->4->3 [10] 5/-1/-1->4->3 [11] 5/-1/-1->4->3 [12] 5/-1/-1->4->3 [13] 5/-1/-1->4->3 [14] 5/-1/-1->4->3 [15] 5/-1/-1->4->3 [16] 5/-1/-1->4->3 [17] 5/-1/-1->4->3 [18] 5/-1/-1->4->3 [19] 5/-1/-1->4->3 [20] 5/-1/-1->4->3 [21] 5/-1/-1->4->3 [22] 5/-1/-1->4->3 [23] 5/-1/-1->4->3 | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO comm 0x555ba0534fd0 rank 7 nRanks 8 nNodes 1 localRanks 8 localRank 7 MNNVL 0 | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO comm 0x555ba114a940 rank 6 nRanks 8 nNodes 1 localRanks 8 localRank 6 MNNVL 0 | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Trees [0] -1/-1/-1->7->6 [1] -1/-1/-1->7->6 [2] -1/-1/-1->7->6 [3] -1/-1/-1->7->6 [4] -1/-1/-1->7->6 [5] -1/-1/-1->7->6 [6] -1/-1/-1->7->6 [7] -1/-1/-1->7->6 [8] -1/-1/-1->7->6 [9] -1/-1/-1->7->6 [10] -1/-1/-1->7->6 [11] -1/-1/-1->7->6 [12] -1/-1/-1->7->6 [13] -1/-1/-1->7->6 [14] -1/-1/-1->7->6 [15] -1/-1/-1->7->6 [16] -1/-1/-1->7->6 [17] -1/-1/-1->7->6 [18] -1/-1/-1->7->6 [19] -1/-1/-1->7->6 [20] -1/-1/-1->7->6 [21] -1/-1/-1->7->6 [22] -1/-1/-1->7->6 [23] -1/-1/-1->7->6 | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO comm 0x555b9f749730 rank 5 nRanks 8 nNodes 1 localRanks 8 localRank 5 MNNVL 0 | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Trees [0] 7/-1/-1->6->5 [1] 7/-1/-1->6->5 [2] 7/-1/-1->6->5 [3] 7/-1/-1->6->5 [4] 7/-1/-1->6->5 [5] 7/-1/-1->6->5 [6] 7/-1/-1->6->5 [7] 7/-1/-1->6->5 [8] 7/-1/-1->6->5 [9] 7/-1/-1->6->5 [10] 7/-1/-1->6->5 [11] 7/-1/-1->6->5 [12] 7/-1/-1->6->5 [13] 7/-1/-1->6->5 [14] 7/-1/-1->6->5 [15] 7/-1/-1->6->5 [16] 7/-1/-1->6->5 [17] 7/-1/-1->6->5 [18] 7/-1/-1->6->5 [19] 7/-1/-1->6->5 [20] 7/-1/-1->6->5 [21] 7/-1/-1->6->5 [22] 7/-1/-1->6->5 [23] 7/-1/-1->6->5 | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Trees [0] 6/-1/-1->5->4 [1] 6/-1/-1->5->4 [2] 6/-1/-1->5->4 [3] 6/-1/-1->5->4 [4] 6/-1/-1->5->4 [5] 6/-1/-1->5->4 [6] 6/-1/-1->5->4 [7] 6/-1/-1->5->4 [8] 6/-1/-1->5->4 [9] 6/-1/-1->5->4 [10] 6/-1/-1->5->4 [11] 6/-1/-1->5->4 [12] 6/-1/-1->5->4 [13] 6/-1/-1->5->4 [14] 6/-1/-1->5->4 [15] 6/-1/-1->5->4 [16] 6/-1/-1->5->4 [17] 6/-1/-1->5->4 [18] 6/-1/-1->5->4 [19] 6/-1/-1->5->4 [20] 6/-1/-1->5->4 [21] 6/-1/-1->5->4 [22] 6/-1/-1->5->4 [23] 6/-1/-1->5->4 | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO comm 0x555ba0547ff0 rank 2 nRanks 8 nNodes 1 localRanks 8 localRank 2 MNNVL 0 | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO comm 0x555ba0549a40 rank 3 nRanks 8 nNodes 1 localRanks 8 localRank 3 MNNVL 0 | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO comm 0x555b9f748ea0 rank 1 nRanks 8 nNodes 1 localRanks 8 localRank 1 MNNVL 0 | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Trees [0] 3/-1/-1->2->1 [1] 3/-1/-1->2->1 [2] 3/-1/-1->2->1 [3] 3/-1/-1->2->1 [4] 3/-1/-1->2->1 [5] 3/-1/-1->2->1 [6] 3/-1/-1->2->1 [7] 3/-1/-1->2->1 [8] 3/-1/-1->2->1 [9] 3/-1/-1->2->1 [10] 3/-1/-1->2->1 [11] 3/-1/-1->2->1 [12] 3/-1/-1->2->1 [13] 3/-1/-1->2->1 [14] 3/-1/-1->2->1 [15] 3/-1/-1->2->1 [16] 3/-1/-1->2->1 [17] 3/-1/-1->2->1 [18] 3/-1/-1->2->1 [19] 3/-1/-1->2->1 [20] 3/-1/-1->2->1 [21] 3/-1/-1->2->1 [22] 3/-1/-1->2->1 [23] 3/-1/-1->2->1 | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Trees [0] 2/-1/-1->1->0 [1] 2/-1/-1->1->0 [2] 2/-1/-1->1->0 [3] 2/-1/-1->1->0 [4] 2/-1/-1->1->0 [5] 2/-1/-1->1->0 [6] 2/-1/-1->1->0 [7] 2/-1/-1->1->0 [8] 2/-1/-1->1->0 [9] 2/-1/-1->1->0 [10] 2/-1/-1->1->0 [11] 2/-1/-1->1->0 [12] 2/-1/-1->1->0 [13] 2/-1/-1->1->0 [14] 2/-1/-1->1->0 [15] 2/-1/-1->1->0 [16] 2/-1/-1->1->0 [17] 2/-1/-1->1->0 [18] 2/-1/-1->1->0 [19] 2/-1/-1->1->0 [20] 2/-1/-1->1->0 [21] 2/-1/-1->1->0 [22] 2/-1/-1->1->0 [23] 2/-1/-1->1->0 | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Trees [0] 4/-1/-1->3->2 [1] 4/-1/-1->3->2 [2] 4/-1/-1->3->2 [3] 4/-1/-1->3->2 [4] 4/-1/-1->3->2 [5] 4/-1/-1->3->2 [6] 4/-1/-1->3->2 [7] 4/-1/-1->3->2 [8] 4/-1/-1->3->2 [9] 4/-1/-1->3->2 [10] 4/-1/-1->3->2 [11] 4/-1/-1->3->2 [12] 4/-1/-1->3->2 [13] 4/-1/-1->3->2 [14] 4/-1/-1->3->2 [15] 4/-1/-1->3->2 [16] 4/-1/-1->3->2 [17] 4/-1/-1->3->2 [18] 4/-1/-1->3->2 [19] 4/-1/-1->3->2 [20] 4/-1/-1->3->2 [21] 4/-1/-1->3->2 [22] 4/-1/-1->3->2 [23] 4/-1/-1->3->2 | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO comm 0x555bab11e710 rank 0 nRanks 8 nNodes 1 localRanks 8 localRank 0 MNNVL 0 | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 00/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 01/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 02/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 03/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 04/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 05/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 06/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 07/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 08/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 09/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 10/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 11/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 12/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 13/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 14/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 15/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 16/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 17/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 18/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 19/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 20/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 21/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 22/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 23/24 : 0 1 2 3 4 5 6 7 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Trees [0] 1/-1/-1->0->-1 [1] 1/-1/-1->0->-1 [2] 1/-1/-1->0->-1 [3] 1/-1/-1->0->-1 [4] 1/-1/-1->0->-1 [5] 1/-1/-1->0->-1 [6] 1/-1/-1->0->-1 [7] 1/-1/-1->0->-1 [8] 1/-1/-1->0->-1 [9] 1/-1/-1->0->-1 [10] 1/-1/-1->0->-1 [11] 1/-1/-1->0->-1 [12] 1/-1/-1->0->-1 [13] 1/-1/-1->0->-1 [14] 1/-1/-1->0->-1 [15] 1/-1/-1->0->-1 [16] 1/-1/-1->0->-1 [17] 1/-1/-1->0->-1 [18] 1/-1/-1->0->-1 [19] 1/-1/-1->0->-1 [20] 1/-1/-1->0->-1 [21] 1/-1/-1->0->-1 [22] 1/-1/-1->0->-1 [23] 1/-1/-1->0->-1 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO P2P Chunksize set to 524288 | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 00/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 01/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 02/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 03/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 04/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 05/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 06/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 00/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 07/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 01/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 08/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 02/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 09/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 03/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 10/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 04/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 11/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 00/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 00/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 05/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 12/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 00/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 01/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 00/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 01/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 06/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 13/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 01/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 01/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 02/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 02/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 07/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 14/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 02/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 02/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 03/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 03/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 08/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 15/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 03/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 03/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 04/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 00/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 04/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 09/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 16/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 04/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 05/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 04/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 01/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 05/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 10/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 00/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 17/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 05/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 06/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 05/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 02/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 06/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 11/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 01/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 18/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 06/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 07/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 06/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 03/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 07/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 12/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 02/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 19/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 07/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 08/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 07/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 04/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 08/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 13/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 03/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 20/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 08/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 09/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 08/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 05/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 14/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 09/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 04/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 21/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 09/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 10/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 06/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 09/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 15/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 10/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 05/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 22/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 11/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 10/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 07/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 10/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 16/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 11/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 06/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 23/0 : 4[4] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 12/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 11/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 08/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 17/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 11/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 12/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 07/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 13/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 12/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 09/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 18/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 12/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 13/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 08/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 14/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 13/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 10/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 19/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 13/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 14/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 09/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 15/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 14/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 11/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 20/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 14/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 15/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 10/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 16/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 12/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 15/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 21/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 15/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 16/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 11/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 17/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 13/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 16/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 22/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 16/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 17/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 18/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 12/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 14/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 17/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 23/0 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 17/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 19/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 18/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 13/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 15/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 18/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 18/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 20/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 16/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 14/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 19/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 19/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 19/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 21/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 17/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 15/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 20/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 20/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 20/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 22/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 18/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 16/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 21/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 21/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 21/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 23/0 : 3[3] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 19/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 22/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 17/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 22/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 22/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 20/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 18/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 23/0 : 2[2] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 21/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 23/0 : 6[6] -> 7[7] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 23/0 : 5[5] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 19/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 22/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 20/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 23/0 : 1[1] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 21/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 22/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Channel 23/0 : 0[0] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Connected all rings | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Connected all rings | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Connected all rings | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Connected all rings | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Connected all rings | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Connected all rings | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Connected all rings | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Connected all rings | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 00/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 01/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 02/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 03/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 04/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 05/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 06/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 07/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 08/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 09/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 10/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 11/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 12/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 13/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 14/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 15/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 16/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 17/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 18/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 00/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 19/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 00/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 01/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 20/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 00/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 01/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 00/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 02/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 21/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 01/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 02/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 01/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 03/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 22/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 02/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 03/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 02/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 04/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Channel 23/0 : 7[7] -> 6[6] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 04/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 03/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 05/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 03/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 00/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 05/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 04/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 00/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 06/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 04/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 06/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 01/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 05/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 01/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 07/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 05/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 07/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 02/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 06/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 02/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 08/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 06/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 08/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 03/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 07/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 03/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 09/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 07/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 04/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 09/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 08/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 04/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 10/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 08/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 05/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 10/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 05/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 09/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 11/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 06/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 09/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 11/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 06/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 10/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 12/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 10/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 07/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 12/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 07/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 11/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 13/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 11/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 13/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 08/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 08/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 12/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 14/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 12/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 14/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 09/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 09/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 15/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 13/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 13/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 15/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 10/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 10/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 16/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 14/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 14/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 16/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 11/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 11/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 17/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 15/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 17/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 15/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 12/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 12/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 18/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 16/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 18/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 16/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 13/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 13/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 19/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 17/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 19/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 17/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 14/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 14/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 20/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 18/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 20/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 18/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 15/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 15/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 21/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 19/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 21/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 19/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 16/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 16/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 22/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 20/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 22/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 20/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 17/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 17/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Channel 23/0 : 4[4] -> 3[3] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 21/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Channel 23/0 : 2[2] -> 1[1] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 21/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 18/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 18/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 22/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 22/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 19/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 19/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Channel 23/0 : 5[5] -> 4[4] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 20/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Channel 23/0 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 20/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 21/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 21/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 22/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 22/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Channel 23/0 : 3[3] -> 2[2] via P2P/IPC/read | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Channel 23/0 : 6[6] -> 5[5] via P2P/IPC/read | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO Connected all trees | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO Connected all trees | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO Connected all trees | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO Connected all trees | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO Connected all trees | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO Connected all trees | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO Connected all trees | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO Connected all trees | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO threadThresholds 8/8/64 | 64/8/64 | 512 | 512 | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO 24 coll channels, 0 collnet channels, 0 nvls channels, 32 p2p channels, 32 p2p channels per peer | |
INFO 2024-07-27 18:38:01,005 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 8/80 | |
tyler-rhel-newimage:826:1366 [3] NCCL INFO comm 0x555ba0549a40 rank 3 nranks 8 cudaDev 3 nvmlDev 3 busId a040 commId 0xd56327a586613906 - Init COMPLETE | |
tyler-rhel-newimage:828:1370 [5] NCCL INFO comm 0x555b9f749730 rank 5 nranks 8 cudaDev 5 nvmlDev 5 busId c060 commId 0xd56327a586613906 - Init COMPLETE | |
tyler-rhel-newimage:830:1364 [7] NCCL INFO comm 0x555ba0534fd0 rank 7 nranks 8 cudaDev 7 nvmlDev 7 busId e080 commId 0xd56327a586613906 - Init COMPLETE | |
tyler-rhel-newimage:827:1368 [4] NCCL INFO comm 0x555b9f749530 rank 4 nranks 8 cudaDev 4 nvmlDev 4 busId c050 commId 0xd56327a586613906 - Init COMPLETE | |
tyler-rhel-newimage:824:1367 [1] NCCL INFO comm 0x555b9f748ea0 rank 1 nranks 8 cudaDev 1 nvmlDev 1 busId 8020 commId 0xd56327a586613906 - Init COMPLETE | |
tyler-rhel-newimage:829:1369 [6] NCCL INFO comm 0x555ba114a940 rank 6 nranks 8 cudaDev 6 nvmlDev 6 busId e070 commId 0xd56327a586613906 - Init COMPLETE | |
tyler-rhel-newimage:825:1365 [2] NCCL INFO comm 0x555ba0547ff0 rank 2 nranks 8 cudaDev 2 nvmlDev 2 busId a030 commId 0xd56327a586613906 - Init COMPLETE | |
tyler-rhel-newimage:801:1363 [0] NCCL INFO comm 0x555bab11e710 rank 0 nranks 8 cudaDev 0 nvmlDev 0 busId 8010 commId 0xd56327a586613906 - Init COMPLETE | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 00/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 00/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 00/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 01/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 01/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 00/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 02/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 02/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 01/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 03/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 03/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 01/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 02/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 04/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 04/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 02/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 03/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 05/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 05/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 03/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 04/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 06/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 06/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 04/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 07/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 05/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 08/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 06/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 05/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 07/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 09/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 06/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 07/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 08/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 10/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 08/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 07/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 09/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 11/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 08/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 09/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 10/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 12/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 10/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 09/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 11/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 13/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 10/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 11/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 12/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 14/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 11/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 12/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 15/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 13/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 16/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 13/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 12/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 14/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 17/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 14/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 13/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 15/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 18/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 15/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 14/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 16/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 19/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 00/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 00/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 00/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 20/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 15/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 17/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 01/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 16/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 01/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 01/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 21/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 16/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 18/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 02/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 02/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 17/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 02/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 22/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 17/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 19/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 03/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 03/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 18/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 03/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 23/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 18/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 20/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 04/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 04/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 19/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 04/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 24/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 05/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 19/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 05/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 21/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 20/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 05/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 25/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 20/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 06/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 06/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 22/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 21/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 06/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 26/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 07/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 07/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 23/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 21/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 08/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 27/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 22/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 07/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 08/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 24/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 22/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 09/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 28/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 23/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 08/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 09/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 25/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 10/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 29/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 23/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 24/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 10/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 09/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 11/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 26/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 30/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 24/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 25/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 11/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 10/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 12/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 25/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:830:1604 [7] NCCL INFO Channel 31/1 : 7[7] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 26/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 27/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 13/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 12/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 11/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 27/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 26/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 28/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 14/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 13/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 12/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 28/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 27/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 15/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 29/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 14/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 13/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 28/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 30/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 29/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 16/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 15/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 14/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 29/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:827:1603 [4] NCCL INFO Channel 31/1 : 4[4] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 30/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 17/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 16/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 15/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 30/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 18/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:829:1605 [6] NCCL INFO Channel 31/1 : 6[6] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 17/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 16/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:828:1606 [5] NCCL INFO Channel 31/1 : 5[5] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 19/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 18/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 17/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 20/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 19/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 18/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 21/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 20/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 19/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 22/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 21/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 20/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 23/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 22/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 24/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 21/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 23/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 25/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 26/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 24/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 22/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 27/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 25/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 23/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 28/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 24/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 26/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 29/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 27/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 25/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 30/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 28/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 26/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:826:1608 [3] NCCL INFO Channel 31/1 : 3[3] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 29/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 27/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 30/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 28/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:824:1609 [1] NCCL INFO Channel 31/1 : 1[1] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 29/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 30/1 : 2[2] -> 0[0] via P2P/IPC/read | |
tyler-rhel-newimage:825:1610 [2] NCCL INFO Channel 31/1 : 2[2] -> 0[0] via P2P/IPC/read | |
INFO 2024-07-27 18:38:05,545 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 9/80 | |
INFO 2024-07-27 18:38:10,412 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 10/80 | |
INFO 2024-07-27 18:38:15,137 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 11/80 | |
INFO 2024-07-27 18:38:19,746 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 12/80 | |
INFO 2024-07-27 18:38:24,535 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 13/80 | |
INFO 2024-07-27 18:38:29,159 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 14/80 | |
INFO 2024-07-27 18:38:33,998 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 15/80 | |
INFO 2024-07-27 18:38:38,748 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 16/80 | |
embedding_mode is False. Embedding API will not work. | |
INFO: Started server process [801] | |
INFO: Waiting for application startup. | |
INFO: Application startup complete. | |
INFO: Uvicorn running on http://127.0.0.1:59587 (Press CTRL+C to quit) | |
INFO 2024-07-27 18:38:43,526 instructlab.model.backends.backends:336: Waiting for the vLLM server to start at http://127.0.0.1:59587/v1, this might take a moment... Attempt: 17/80 | |
INFO: 127.0.0.1:49680 - "GET /v1/models HTTP/1.1" 200 OK | |
INFO 2024-07-27 18:38:43,530 instructlab.model.backends.backends:343: vLLM engine successfully started at http://127.0.0.1:59587/v1 | |
0%| | 0/160 [00:00<?, ?it/s]INFO: 127.0.0.1:49756 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49684 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
1%|█▎ | 1/160 [00:05<13:19, 5.03s/it]INFO: 127.0.0.1:49808 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49794 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49698 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49702 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49832 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
1%|██▌ | 2/160 [00:05<06:49, 2.59s/it]INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49762 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49822 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49778 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49716 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
2%|█████ | 4/160 [00:10<06:07, 2.36s/it]INFO: 127.0.0.1:49836 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49742 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49684 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49808 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49716 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49740 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49756 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49794 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49832 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49822 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49778 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49742 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49702 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49836 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49740 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49756 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49724 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
3%|██████▎ | 5/160 [00:19<11:20, 4.39s/it]INFO: 127.0.0.1:49684 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49836 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49832 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49698 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
13%|██████████████████████████▎ | 21/160 [00:19<01:20, 1.73it/s]INFO: 127.0.0.1:49742 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49808 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49724 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49832 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49778 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49740 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49716 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49808 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49836 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49742 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49698 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49762 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
16%|███████████████████████████████▎ | 25/160 [00:23<01:27, 1.55it/s]INFO: 127.0.0.1:49684 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49756 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49740 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49822 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49742 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49832 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49836 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49716 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49756 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49762 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49724 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49794 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
22%|█████████████████████████████████████████████ | 36/160 [00:29<01:14, 1.67it/s]INFO: 127.0.0.1:49836 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49740 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49822 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49684 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49756 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49716 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49742 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49702 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
26%|███████████████████████████████████████████████████▏ | 41/160 [00:31<01:06, 1.78it/s]INFO: 127.0.0.1:49808 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49794 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49832 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49716 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49724 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49836 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49778 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
34%|████████████████████████████████████████████████████████████████████▊ | 55/160 [00:33<00:37, 2.79it/s]INFO: 127.0.0.1:49698 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
39%|█████████████████████████████████████████████████████████████████████████████▌ | 62/160 [00:33<00:26, 3.69it/s]INFO: 127.0.0.1:49756 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49702 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49762 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
46%|████████████████████████████████████████████████████████████████████████████████████████████▌ | 74/160 [00:35<00:18, 4.68it/s]INFO: 127.0.0.1:49698 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49808 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49756 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49832 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49702 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49724 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49822 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49684 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49794 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49740 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
49%|██████████████████████████████████████████████████████████████████████████████████████████████████▊ | 79/160 [00:39<00:27, 2.89it/s]INFO: 127.0.0.1:49698 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49762 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49778 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49756 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49702 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49742 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
53%|██████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 85/160 [00:41<00:23, 3.24it/s]INFO: 127.0.0.1:49832 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49794 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49808 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49822 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49742 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49716 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
56%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌ | 90/160 [00:43<00:24, 2.82it/s]INFO: 127.0.0.1:49702 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49762 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49698 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49794 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49756 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49724 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49684 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49808 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49822 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49762 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49742 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49778 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49762 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49684 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49832 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49808 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49740 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49836 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
58%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 93/160 [00:48<00:36, 1.83it/s]INFO: 127.0.0.1:49698 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49742 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49684 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49702 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49762 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
72%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 115/160 [00:50<00:12, 3.59it/s]INFO: 127.0.0.1:49836 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49778 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49740 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49684 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49698 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49724 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49794 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49836 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49742 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49702 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49716 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
76%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 122/160 [00:53<00:11, 3.18it/s]INFO: 127.0.0.1:49684 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49698 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49794 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49740 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49762 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49822 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49716 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49824 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49808 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49698 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49778 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49794 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49684 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49756 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
79%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 127/160 [00:57<00:13, 2.52it/s]INFO: 127.0.0.1:49702 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49836 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49742 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49724 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
INFO: 127.0.0.1:49832 - "POST /v1/chat/completions HTTP/1.1" 200 OK | |
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 160/160 [01:11<00:00, 2.24it/s] | |
INFO: Shutting down | |
INFO: Waiting for application shutdown. | |
INFO: Application shutdown complete. | |
INFO: Finished server process [801] | |
[rank0]:[W CudaIPCTypes.cpp:16] Producer process has been terminated before all shared CUDA tensors released. See Note [Sharing CUDA tensors] | |
/usr/lib64/python3.11/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 1 leaked shared_memory objects to clean up at shutdown | |
warnings.warn('resource_tracker: There appear to be %d ' | |
# SKILL EVALUATION REPORT | |
## MODEL | |
/var/instructlabbigdisk/instructlab/skillscheckpoints/hf_format/samples_1056/ | |
### AVERAGE: | |
4.16 (across 158) | |
### TURN ONE: | |
5.54 | |
### TURN TWO: | |
2.77 | |
### ERROR RATE: | |
0.01 | |
[root@tyler-rhel-newimage instructlab]# |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment