yyccli's Stars
donnemartin/system-design-primer
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
ggerganov/llama.cpp
LLM inference in C/C++
facebookresearch/llama
Inference code for LLaMA models
llvm/llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Dao-AILab/flash-attention
Fast and memory-efficient exact attention
apache/tvm
Open deep learning compiler stack for cpu, gpu and specialized accelerators
openai/triton
Development repository for the Triton language and compiler
NVIDIA/TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
NVIDIA/Megatron-LM
Ongoing research training transformer models at scale
NVIDIA/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.
facebookresearch/llama-recipes
Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger
NVIDIA/cuda-samples
Samples for CUDA Developers which demonstrates features in CUDA Toolkit
NVIDIA/FasterTransformer
Transformer related optimization, including BERT, GPT
NVIDIA/cutlass
CUDA Templates for Linear Algebra Subroutines
theicfire/makefiletutorial
Learn make by example
facebookincubator/AITemplate
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
openmlsys/openmlsys-zh
《Machine Learning Systems: Design and Implementation》- Chinese Version
sjtug/SJTUThesis
上海交通大学 LaTeX 论文模板 | Shanghai Jiao Tong University LaTeX Thesis Template
NVIDIA/nccl
Optimized primitives for collective multi-GPU communication
BBuf/tvm_mlir_learn
compiler learning resources collect.
NVIDIA/CUDALibrarySamples
CUDA Library Samples
zwang4/awesome-machine-learning-in-compilers
Must read research papers and links to tools and datasets that are related to using machine learning for compilers and systems optimisation
BBuf/how-to-optim-algorithm-in-cuda
how to optimize some algorithm in cuda.
d2l-ai/d2l-tvm
Dive into Deep Learning Compiler
tanjeffreyz/auto-maple
Artificial intelligence software for MapleStory that uses various machine learning and computer vision techniques to navigate challenging in-game environments
openxla/stablehlo
Backward compatible ML compute opset inspired by HLO/MHLO
alibaba/heterogeneity-aware-lowering-and-optimization
heterogeneity-aware-lowering-and-optimization
Lewuathe/mlir-hello
MLIR Sample dialect
GouMinghao/new_SJTU_thesis_template
SJTU thesis template version 2021, modified from the official version