Skip to content

Instantly share code, notes, and snippets.

@jerryzh168
Created December 17, 2024 23:54
Show Gist options
  • Save jerryzh168/1542b036b8f1ed0777a9e7fb0a629acb to your computer and use it in GitHub Desktop.
Save jerryzh168/1542b036b8f1ed0777a9e7fb0a629acb to your computer and use it in GitHub Desktop.
[2024-12-17 15:09:47 TP0] Decode batch. #running-req: 968, #token: 511530, token usage: 0.11, gen throughput (token/s): 1554.84, #queue-req: 0
[2024-12-17 15:09:48 TP0] Decode batch. #running-req: 922, #token: 523719, token usage: 0.11, gen throughput (token/s): 47852.88, #queue-req: 0
[2024-12-17 15:09:49 TP0] Decode batch. #running-req: 883, #token: 535168, token usage: 0.11, gen throughput (token/s): 46588.76, #queue-req: 0
[2024-12-17 15:09:50 TP0] Decode batch. #running-req: 847, #token: 548080, token usage: 0.11, gen throughput (token/s): 44284.98, #queue-req: 0
[2024-12-17 15:09:50 TP0] Decode batch. #running-req: 799, #token: 545397, token usage: 0.11, gen throughput (token/s): 42336.33, #queue-req: 0
[2024-12-17 15:09:51 TP0] Decode batch. #running-req: 767, #token: 556549, token usage: 0.12, gen throughput (token/s): 41241.09, #queue-req: 0
[2024-12-17 15:09:52 TP0] Decode batch. #running-req: 730, #token: 558371, token usage: 0.12, gen throughput (token/s): 39677.03, #queue-req: 0
[2024-12-17 15:09:53 TP0] Decode batch. #running-req: 696, #token: 563059, token usage: 0.12, gen throughput (token/s): 40466.68, #queue-req: 0
[2024-12-17 15:09:53 TP0] Decode batch. #running-req: 659, #token: 560803, token usage: 0.12, gen throughput (token/s): 39211.28, #queue-req: 0
[2024-12-17 15:09:54 TP0] Decode batch. #running-req: 620, #token: 554893, token usage: 0.12, gen throughput (token/s): 36115.87, #queue-req: 0
[2024-12-17 15:09:55 TP0] Decode batch. #running-req: 578, #token: 541785, token usage: 0.11, gen throughput (token/s): 33475.34, #queue-req: 0
[2024-12-17 15:09:55 TP0] Decode batch. #running-req: 539, #token: 526772, token usage: 0.11, gen throughput (token/s): 30931.34, #queue-req: 0
[2024-12-17 15:09:56 TP0] Decode batch. #running-req: 497, #token: 506839, token usage: 0.11, gen throughput (token/s): 30879.31, #queue-req: 0
[2024-12-17 15:09:57 TP0] Decode batch. #running-req: 463, #token: 487930, token usage: 0.10, gen throughput (token/s): 29039.67, #queue-req: 0
[2024-12-17 15:09:57 TP0] Decode batch. #running-req: 429, #token: 469028, token usage: 0.10, gen throughput (token/s): 26853.83, #queue-req: 0
[2024-12-17 15:09:58 TP0] Decode batch. #running-req: 397, #token: 447854, token usage: 0.09, gen throughput (token/s): 25042.27, #queue-req: 0
[2024-12-17 15:09:59 TP0] Decode batch. #running-req: 360, #token: 423961, token usage: 0.09, gen throughput (token/s): 22531.09, #queue-req: 0
[2024-12-17 15:09:59 TP0] Decode batch. #running-req: 322, #token: 392631, token usage: 0.08, gen throughput (token/s): 20247.99, #queue-req: 0
[2024-12-17 15:10:00 TP0] Decode batch. #running-req: 283, #token: 356022, token usage: 0.07, gen throughput (token/s): 18830.85, #queue-req: 0
[2024-12-17 15:10:01 TP0] Decode batch. #running-req: 244, #token: 314040, token usage: 0.07, gen throughput (token/s): 16444.89, #queue-req: 0
[2024-12-17 15:10:01 TP0] Decode batch. #running-req: 208, #token: 274492, token usage: 0.06, gen throughput (token/s): 14763.47, #queue-req: 0
[2024-12-17 15:10:02 TP0] Decode batch. #running-req: 162, #token: 214014, token usage: 0.04, gen throughput (token/s): 11658.93, #queue-req: 0
[2024-12-17 15:10:02 TP0] Decode batch. #running-req: 119, #token: 166334, token usage: 0.03, gen throughput (token/s): 20221.47, #queue-req: 0
[2024-12-17 15:10:02 TP0] Decode batch. #running-req: 86, #token: 122490, token usage: 0.03, gen throughput (token/s): 17708.82, #queue-req: 0
[2024-12-17 15:10:03 TP0] Decode batch. #running-req: 42, #token: 59365, token usage: 0.01, gen throughput (token/s): 12091.23, #queue-req: 0
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment