Lists (19)
Agent Skills & Tooling
Claude Skills 生态、agent harness 工具48 repositories
AI Agent Frameworks
Claude/LangChain/LangGraph/MCP/Agent SDK113 repositories
AI Infra Learning (中文)
中文 AI infra/LLM 教程与 awesome list33 repositories
Container Runtimes / Wasm
containerd/runc/kata/youki/wasm27 repositories
CS Fundamentals / Interview
算法、系统设计、面试题、经典书29 repositories
Go & Rust Foundations
Go/Rust 语言学习、基础库、Web 框架89 repositories
K8s × AI Serving
K8s 上跑 LLM/AI 工作负载的平台45 repositories
K8s Core & Controllers
K8s 主线、controllers、operator SDK、CRD、kubectl、client-go360 repositories
K8s GPU & Device Plugins
GPU/异构、device-plugin、DRA、vGPU36 repositories
K8s Multi-Cluster & Edge
多集群、虚拟集群、边缘32 repositories
K8s Networking & CNI
CNI、Service Mesh、Envoy、Gateway47 repositories
K8s Schedulers & Batch
调度器、队列、batch、Volcano/Kueue/Karpenter/Koordinator54 repositories
LLM Inference Engines
vLLM/SGLang/LMDeploy/Ollama/TensorRT/Dynamo65 repositories
LLM Training & Fine-tuning
训练、微调、量化30 repositories
Misc / Personal Tools
其余工具与个人项目212 repositories
My / Friends' Projects
自己仓库 + 学习圈仓库58 repositories
Observability & Tracing
Prom/Grafana/OTel/Loki/Pyroscope/eBPF observability69 repositories
Quant / Finance
量化交易、金融数据10 repositories
Storage on K8s
CSI、本地存储、缓存、数据加速22 repositories
Starred repositories
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
LUPINE is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.
LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure
An inference control plane for Kubernetes and vLLM
CSAPP 中文文档与学习资料：《深入理解计算机系统》第三版全章节 Markdown，含练习题答案、八大实验中文翻译及官方自学实验包，方便在线阅读与离线学习。
Towards a More Autonomous Agent System
Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.
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。
高性价比人生指南: 长寿防病、急救、省钱理财、法律红线、失业与工伤、医保社保、恋爱婚育、怀孕育儿、创业与做平台合规、出国与技能。每条写明成本、收益、证据等级和原始出处，只引期刊论文与官方文件。
AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and supp…
GPT-Image-2 PPT Generator Skill for Creating Image-Based PowerPoint Presentations in Codex and Other Skill-Compatible Agents
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Your Cheat Sheet for AI Engineering Interview – Questions and Answers.
Your Cheat Sheet For AI Engineering Interviews at Top AI Companies - Questions and Answers.
Community maintained hardware plugin for vLLM on Huawei Ascend
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
FlashMLA: Efficient Multi-head Latent Attention Kernels
Reverse engineer anything with agents, from app behavior down to native binaries.
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create motion, prototypes, websites, apps, dashboards, presentations, images, and videos with your team and AI agents. …
Write HTML. Render video. Built for agents.
Community maintained hardware plugin for vLLM on Apple Silicon
Model Express is a Rust-based component meant to be placed next to existing model inference systems to speed up their startup times and improve overall performance.