Cuiqing Li (李崔卿) tiandiao123

AI Framework Engineer@AI Startup(上海), previous @ Meta(PyTorch), Bytedance (AML, AI LAB), Contributor of TVM, PyTorch and Colossal-AI

tiandiao123 / cutlass_gemm_tensorcore.py

Last active August 8, 2023 13:42

	#include <cublas_v2.h>
	#include <cstdint>
	#include <cuda.h>
	#include <cuda_runtime.h>
	#include <cuda_fp16.h>
	#include <iostream>
	#include <torch/torch.h>

	#include "cutlass/cutlass.h"
	#include "cutlass/gemm/device/gemm_splitk_parallel.h"

tiandiao123 / gemm_test.cu

Created August 9, 2023 07:21

tiandiao123 / new_gemm.cu

Last active August 9, 2023 07:34

tiandiao123 / cutlass_gemm.py

Created August 10, 2023 04:30

tiandiao123 / test.py

Created September 21, 2023 16:47

	import inspect
	from typing import Any, Callable, Dict, List, Optional, Tuple, Union

	import PIL.Image
	import torch
	from transformers import CLIPTextModel, CLIPTextModelWithProjection, CLIPTokenizer
	from diffusers import StableDiffusionXLImg2ImgPipeline

	from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
	from diffusers.loaders import FromSingleFileMixin, StableDiffusionXLLoraLoaderMixin, TextualInversionLoaderMixin

tiandiao123 / vllm_benchmark.py

Last active October 17, 2023 03:45

vllm_benchmark.py

	from vllm import LLM, SamplingParams
	import torch
	from torch import distributed as dist
	import time
	from tqdm import tqdm
	import numpy as np

	# # Create an LLM.
	llm = LLM(
	model="/home/lclcq/share/llama-7b",

tiandiao123 / benchmark_llama2_colossal_infer.py

Created November 18, 2023 08:36

	import os
	import warnings
	import time

	import torch
	import torch.distributed as dist
	import argparse
	from packaging import version

	import colossalai

tiandiao123 / benchmark_llama.py

Created November 18, 2023 16:37

	import argparse
	import os
	import time

	import torch
	from _utils import print_perf_stats
	from transformers import LlamaForCausalLM, LlamaTokenizer

	import colossalai
	from colossalai.inference.tensor_parallel.engine import TPInferEngine

tiandiao123 / vllm_test.py

Created November 18, 2023 16:41

	from vllm import LLM, SamplingParams
	import torch
	from torch import distributed as dist
	import time
	from tqdm import tqdm
	import numpy as np

	# # Create an LLM.
	llm = LLM(
	model="/home/lclcq/share/llama-7b",

tiandiao123 / bench_colossal_llama2.py

Created November 19, 2023 05:18

	import os
	import warnings
	import time

	import torch
	import torch.distributed as dist
	import argparse
	from packaging import version

	import colossalai