🚀🧠💬 Supercharged Custom Instructions for ChatGPT (non-coding) and ChatGPT Advanced Data Analysis (coding).

Sparsity-aware deep learning inference runtime for CPUs

A programming framework for agentic AI 🤖

LLMs as Copilots for Theorem Proving in Lean

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

An LLM playground you can run on your laptop

An innovative library for efficient LLM inference via low-bit quantization

AI模型接口管理与分发系统，支持将多种大模型转为OpenAI格式调用、支持Midjourney Proxy、Suno、Rerank，兼容易支付协议，仅供个人或者企业内部管理与分发渠道使用，请勿用于商业用途，本项目基于One API二次开发。

Every front-end GUI client for ChatGPT

LLM training in simple, raw C/CUDA

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

Large-scale LLM inference engine

Efficient Triton Kernels for LLM Training

An acceleration library that supports arbitrary bit-width combinatorial quantization operations