A fast inference library for running LLMs locally on modern consumer-class GPUs

Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)

XTuner is a toolkit for efficiently fine-tuning LLM

A high-throughput and memory-efficient inference and serving engine for LLMs

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

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

OpenMMLab Pose Estimation Toolbox and Benchmark.

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

Explorations into Ring Attention, from Liu et al. at Berkeley AI

Robust recipes to align language models with human and AI preferences

AIOS: LLM Agent Operating System

OpenMMLab Foundational Library for Training Deep Learning Models

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

纯c++的全平台llm加速库，chatglm-6B级模型单卡可达10000+token / s，支持moss, chatglm, baichuan模型，手机端流畅运行

An Open-source Toolkit for LLM Development

A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Example deep learning projects that use wandb's features.

An open-source framework for training large multimodal models

WebUI extension for ControlNet

Stable Diffusion web UI

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

OpenMMLab Detection Toolbox and Benchmark

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Building a quick conversation-based search demo with Lepton AI.

OpenMMLab Model Deployment Framework

A Ray-based High-performance RLHF framework (Support 70B+ full tuning & LoRA & Mixtral)

Doing simple retrieval from LLM models at various context lengths to measure accuracy

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

General technology for enabling AI capabilities w/ LLMs and MLLMs