A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…

MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

An LLM post-training framework with vLLM for RL Scaling

⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents -- All for Long running Agentized Workflows

An agent harness that compiles a model into one provably-correct, self-retargeting CUDA megakernel and self-tunes it past cuBLAS at batch-1 LLM decode, paper: https://arxiv.org/abs/2606.09682

Ascend operator generation

Skills for Real Engineers. Straight from my .agents directory.

Lightweight coding agent that runs in your terminal

⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and agentized workflows

本文原文由知名 Hacker Eric S. Raymond 所撰寫，教你如何正確的提出技術問題並獲得你滿意的答案。

Tile-Based Runtime for Ultra-Low-Latency LLM Inference

PTX ISA 9.1 documentation converted to searchable markdown. Includes Claude Code skill for CUDA development.

Community maintained hardware plugin for vLLM on Ascend

启智平台任务管理 CLI：资源查询、任务提交、日志查看和 MCP/agent workflow

Karpathy’s LLM Wiki, 100% local with Ollama. Drop Markdown notes → AI extracts concepts → your Obsidian wiki auto-links and grows. Zero sharing. Your notes stay yours.

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…

App for Codex / Claude Code / Pi / OpenCode / Kimi Code / Grok Build, vibe coding anytime, anywhere

App for Claude Code / Codex / Gemini / OpenCode, vibe coding anytime, anywhere

https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习｜数据合成

Local-first cross-platform desktop workspace for Claude Code / agents: multi-agent, Git worktrees, code diffs, skill marketplace, multi-model, Computer Use, task-aware desktop pets, with WeChat, Fe…

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

From Automated Idea Factory to Realization

Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.

AI agents running research on single-GPU nanochat training automatically

AKG (Auto Kernel Generator) is an optimizer for operators in Deep Learning Networks, which provides the ability to automatically fuse ops with specific patterns.

A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular configuration across SFT, RLVR, and evaluation workflows.