gitover22

CaptchaNetTrainer

A framework for learning deep learning training testing procedures

gitover22

the-Congestion-Control-Process-in-TCP-in-NS-3

Programming Assignment for CN2023: Understanding the Congestion Control Process in TCP in NS-3.

DSF_CNCL

DSM system framework based on CNCL

HF_DFS

HF_DFS is a distributed file system that is built on fastDFS.

SuperServer

based on c/c++, high performance server

Go_notes

记录go语言学习历程

Linux_syscall_demo

test demo for linux syscall.

miniCache

the cache is a simple implementation，with write back/allocation

MiniGPT4-on-MLU

将MiniGPT4移植到MLU370上，可以实现多卡训练和推理功能

ChatStoreHub

cuda-samples

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

LLaMA-infer

A Inference Framework for LLaMA Models

llama-study

Inference code for Llama models

CUDA-Learn-Notes

🎉 CUDA Learn Notes with PyTorch: fp32、fp16/bf16、fp8/int8、flash_attn、sgemm、sgemv、warp/block reduce、dot prod、elementwise、softmax、layernorm、rmsnorm、hist etc.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

glake

GLake: optimizing GPU memory management and IO transmission.

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

nnfusion

A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.

sglang

SGLang is a fast serving framework for large language models and vision language models.

sinfer-project

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

cambricon-pytorch

Build Cambricon PyTorch from source