char-1ee

followers

following

stars

Nanyang Technological University

Singapore

Li Xingjian's starred repositories

experiments

My exploration on new technologies.

Language:PythonMIT800

attorch

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

Language:PythonMIT43700

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

Language:PythonNOASSERTION820700

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

Language:Jupyter NotebookApache-2.01006900

triton

Development repository for the Triton language and compiler

Language:C++MIT1225100

attention_with_linear_biases

Code for the ALiBi method for transformer language models (ICLR 2022)

Language:PythonMIT49400

llm.c

LLM training in simple, raw C/CUDA

Language:CudaMIT2266000

public-apis

A collective list of free APIs

Language:PythonMIT30989500

mistral-inference

Official inference library for Mistral models

Language:Jupyter NotebookApache-2.0942100

gateway

A Blazing Fast AI Gateway with integrated Guardrails. Route to 200+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Language:TypeScriptMIT566500

vim-as-an-ide

Workshop on how to use Vim Plugins.

Language:VimL196800

torchtune

A Native-PyTorch Library for LLM Fine-tuning

Language:PythonBSD-3-Clause377500

Twitter-Insight-LLM

Twitter data scraping, embedding based image search and more.

Language:Jupyter Notebook56900

ttrpc

GRPC for low-memory environments

Language:GoApache-2.053200

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Language:PythonApache-2.0750000

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Language:PythonApache-2.02124400

ring-flash-attention

Ring attention implementation with flash attention

Language:Python48500

pixel-profile

Generate a pixel art style profile card from your GitHub data! ✨

Language:TypeScriptMIT41200

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

Language:Jupyter Notebook1132400

llama.cpp

LLM inference in C/C++

Language:C++MIT6361600

llama

Inference code for Llama models

Language:PythonNOASSERTION5508000

clustershell

Scalable cluster administration Python framework — Manage node sets, node groups and execute commands on cluster nodes in parallel.

Language:Python41600

gradient-checkpointing

Make huge neural nets fit in memory

Language:PythonMIT267500

nccl

Optimized primitives for collective multi-GPU communication

Language:C++NOASSERTION306200

nccl-tests

NCCL Tests

Language:CudaBSD-3-Clause78500

pre-commit

A framework for managing and maintaining multi-language pre-commit hooks.

Language:PythonMIT1258300

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

Language:C++MIT777700

ebpf-for-windows

eBPF implementation that runs on top of Windows

Language:CMIT278200

hotspot

The Linux perf GUI for performance analysis.

Language:C++401200

delve

Delve is a debugger for the Go programming language.

Language:GoMIT2260400