BolinSNLHM's Stars
DefTruth/Awesome-SD-Distributed-Inference
📖A small curated list of Awesome SD/DiT/ViT/Diffusion Distributed Inference(Multi-GPUs) Paper with codes, such as DistriFusion, PipeFusion, AsyncDiff, DeepCache etc.
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
karpathy/llama2.c
Inference Llama 2 in one file of pure C
HazyResearch/ThunderKittens
Tile primitives for speedy kernels
DefTruth/CUDA-Learn-Notes
🎉CUDA 笔记 / 大模型手撕CUDA / C++笔记,更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.
cuda-mode/resource-stream
CUDA related news and material links
DefTruth/Awesome-LLM-Inference
📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.
wangsiping97/FastGEMV
High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
mosharaf/eecs598
Advanced Topics on Systems for X
UofT-EcoSystem/Minuet
[EuroSys'24] Minuet: Accelerating 3D Sparse Convolutions on GPUs
google/XNNPACK
High-efficiency floating-point neural network inference operators for mobile, server, and Web
geekan/HowToLiveLonger
程序员延寿指南 | A programmer's guide to live longer
apache/tvm
Open deep learning compiler stack for cpu, gpu and specialized accelerators
hidet-org/hidet
An open-source efficient deep learning framework/compiler, written in python.
merrymercy/awesome-tensor-compilers
A list of awesome compiler projects and papers for tensor computation and deep learning.
f0rki/mapping-high-level-constructs-to-llvm-ir
A guide that explains how high level programming language constructs are mapped to the LLVM intermediate language.
chenzomi12/AISystem
AISystem 主要是指AI系统,包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
Anduin2017/HowToCook
程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).
oneapi-src/oneDNN
oneAPI Deep Neural Network Library (oneDNN)
codecrafters-io/build-your-own-x
Master programming by recreating your favorite technologies from scratch.
bitterengsci/My-ebook
alwqx/awesome-cs-course
awesome university cs core courses
youngyangyang04/leetcode-master
《代码随想录》LeetCode 刷题攻略:200道经典题目刷题顺序,共60w字的详细图解,视频难点剖析,50余张思维导图,支持C++,Java,Python,Go,JavaScript等多语言版本,从此算法学习不再迷茫!🔥🔥 来看看,你会发现相见恨晚!🚀
PKUFlyingPig/cs-self-learning
计算机自学指南
Urinx/Books
无它术,唯勤读书而多为之,自工
selfteaching/the-craft-of-selfteaching
One has no future if one couldn't teach themself.