Jin-Chuan's Stars
shriramsb/vdnn-plus-plus
Implementation of vDNN++; an improvement over vDNN
andy-yang-1/DoubleSparse
16-fold memory access reduction with nearly no loss
Bruce-Lee-LY/flash_attention_inference
Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.
sgl-project/sglang
SGLang is a fast serving framework for large language models and vision language models.
yandex/YaFSDP
YaFSDP: Yet another Fully Sharded Data Parallel
szagoruyko/pytorchviz
A small package to create visualizations of PyTorch execution graphs
lizhe2004/Awesome-LLM-RAG-Application
the resources about the application based on LLM with RAG pattern
volcengine/veGiantModel
pytorch/PiPPy
Pipeline Parallelism for PyTorch
volcengine/veScale
A PyTorch Native LLM Training Framework
JohanyCheung/notebook
my notebook !
Doragd/Algorithm-Practice-in-Industry
搜索、推荐、广告、用增等工业界实践文章收集(来源:知乎、Datafuntalk、技术公众号)
pytorch/tensorpipe
A tensor-aware point-to-point communication primitive for machine learning
NVIDIA/NeMo
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
getkeops/keops
KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows
skapadia3214/groq-moa
Mixture of Agents using Groq
AlibabaPAI/llumnix
Efficient and easy multi-instance LLM serving
AnswerDotAI/gpu.cpp
A lightweight library for portable low-level GPU computation using WebGPU.
TiledTensor/TiledCUDA
TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.
HazyResearch/ThunderKittens
Tile primitives for speedy kernels
virtaitech/orion
0x5ec1ab/gpu-tlb
microsoft/vattention
Dynamic Memory Management for Serving LLMs without PagedAttention
Lordog/dive-into-llms
《动手学大模型Dive into LLMs》系列编程实践教程
Bruce-Lee-LY/cuda_hook
Hooked CUDA-related dynamic libraries by using automated code generation tools.
tkestack/vcuda-controller
NVIDIA/DALI
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
gradio-app/gradio
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
NVIDIA/open-gpu-kernel-modules
NVIDIA Linux open GPU kernel module source
torvalds/linux
Linux kernel source tree