Agentic Kernel Optimization for All — automated GPU kernel optimization for any kernel, any hardware, any language

Codex++ tweak system for the Codex desktop app

Reference and an example for the Bluetooth API for makers in Claude Cowork & Claude Code Desktop

最好用的 Xray 一键安装脚本 & 管理脚本

AI agents running research on single-GPU nanochat training automatically

A Lightweight LLM Post-Training Library

A simple, performant, and scalable Jax LLM!

JAX backend for SGL

A Survey of Reinforcement Learning for Large Reasoning Models

From search engines, to science, to robotics, this reposity is meant to showcase the use of reinforcement learning in the world..

HyperContainer Daemon

Kubernetes CSI Driver for serving OCI model artifacts

蚂蚁开源技术沙龙演讲材料归档

The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and semi-structured data into a single engine. This all-in-one database makes agents smarter, easier to r…

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)

RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of …

Fast, flexible LLM inference

Data driven agentic landscapes and insights. Produced by Ant Open Source and inclusionAI.

End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.

Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serving systems.

The most widely used Python to C compiler

An open-source AI agent that brings the power of Gemini directly into your terminal.

Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.

Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.

NCCL Tests

Kernels, of the mega variety :)

Command-line tools for managing OCI model artifacts, which are bundled based on Model Spec

The Fastest Distributed Database for Transactional, Analytical, and AI Workloads.

High-performance safetensors model loader