cg

followers

following

stars

Shanghai

Chen Gong's starred repositories

flash-attention

Fast and memory-efficient exact attention

Language:PythonBSD-3-Clause1270400

breakpad

Mirror of Google Breakpad project

Language:C++NOASSERTION258400

remill

Library for lifting machine code to LLVM bitcode

Language:C++Apache-2.0123800

publications

Publications from Trail of Bits

Language:PythonCC-BY-SA-4.0138200

HVM

A massively parallel, optimal functional runtime in Rust

Language:CudaApache-2.01033900

ir

Lightweight JIT Compilation Framework

Language:CMIT33400

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

Language:PythonMIT584100

xed

The X86 Encoder Decoder (XED), is a software library for encoding and decoding X86 (IA32 and Intel64) instructions

Language:PythonApache-2.0138300

zydis

Fast and lightweight x86/x86-64 disassembler and code generation library

Language:CMIT332300

abi-aa

Application Binary Interface for the Arm® Architecture

Language:HTMLNOASSERTION88300

include-what-you-use

A tool for use with clang to analyze #includes in C and C++ source files

Language:C++NOASSERTION401800

gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.

Language:C++Apache-2.0583900

flax

Flax is a neural network library for JAX that is designed for flexibility.

Language:PythonApache-2.0585200

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

CC0-1.0140500

segment-anything-fast

A batched offline inference oriented version of segment-anything

Language:PythonApache-2.0115700

paper-reading

深度学习经典、新论文逐段精读

Apache-2.02537200

Learn-LLVM-17

Learn LLVM 17, published by Packt

Language:C++MIT9700

DirectXShaderCompiler

This repo hosts the source for the DirectX Shader Compiler which is based on LLVM/Clang.

Language:C++NOASSERTION300500

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Language:PythonApache-2.01350400

Fuser

A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")

Language:C++NOASSERTION23900

CppCon2023

Slides and other materials from CppCon 2023

ML-YouTube-Courses

📺 Discover the latest machine learning / AI courses on YouTube.

CC0-1.01459800

annotated_deep_learning_paper_implementations

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

Language:PythonMIT5241400

TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Language:PythonMPL-2.03241200

leptonai

A Pythonic framework to simplify AI service building

Language:PythonApache-2.0260300

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Language:PythonMIT640000

S-LoRA

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

Language:PythonApache-2.0165600

lightllm

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

Language:PythonApache-2.0214500

ggml

Tensor library for machine learning

Language:C++MIT1047900

llama

Inference code for Llama models

Language:PythonNOASSERTION5481400