Stars
Framework for evaluating and improving agents
A simple, fast and robust program-aware agentic inference system.
ASD-STE100 Simplified Technical English rules, repurposed as a Claude Code skill for rewriting ambiguous agent-facing English.
LeaderWorkerSet & DisaggregatedSet: Kubernetes APIs for Distributed and Disaggregated AI Serving
Optimize prompts, code, and more with AI-powered Reflective Optimization
Lightweight coding agent that runs in your terminal
High Performance Serving Runtime For Interactive Super Intelligence System
AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.
llm-d Router: The intelligent entry point for inference requests
《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码
Configuration Agnostic and Redundancy Aware Profiler
LLM serving simulator that uses DoolyProf's latency database; built around the vLLM's native scheduler.
vLLM wall-clock emulation pluging to allow running the real vllm serve and benchmark without gpu with simple mocking
专业的短剧剧本创作skill,从选题立项到分集撰写、质量自检、合规审核、海外出海,覆盖短剧剧本生产全流程。
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
Skills for Real Engineers. Straight from my .agents directory.
[CVPR 2025] A Hierarchical Movie Level Dataset for Long Video Generation
[CVPR 2026] ViStoryBench: AI Story Visualization Benchmark
Open Source AI Accelerator Research Platform Standard / 开源推理研究平台
Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
Moving to vllm-project/vllm-jax. TPU inference for vLLM, with unified JAX and PyTorch support.