Starred repositories
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
A collection of community-sourced DeviceType definitions for import to NetBox
The premier source of truth powering network automation. Open source under Apache 2. Try NetBox Cloud free: https://netboxlabs.com/products/free-netbox-cloud/
Ralph is the CMDB / Asset Management system for data center and back office hardware.
Bot that bridges Feishu/Lark messenger with a local Claude Code or Codex CLI. Streaming cards, per-chat sessions, multiple workspaces
Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?
Standalone vLLM weight-update publisher and RL source-snapshot tooling
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
[Archived] Superseded by humanfia/humanize — workflow-native terminal coding agent, a fork of can1357/oh-my-pi
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
Skills for Real Engineers. Straight from my .agents directory.
Lightweight coding agent that runs in your terminal
PolyArch / oh-my-humanize
Forked from can1357/oh-my-pi⌥ 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。
Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.
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 Huawei 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…