8000 yangligt2 / Starred · GitHub
[go: up one dir, main page]

Skip to content
View yangligt2's full-sized avatar

Block or report yangligt2

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Agent Substrate: the core system

Go 8,108 891 Updated Nov 21, 2026

Framework for evaluating and improving agents

Python 7,325 2,272 Updated Nov 21, 2026

A simple, fast and robust program-aware agentic inference system.

Python 485 53 Updated Jul 5, 2026
JavaScript 30 27 Updated Nov 9, 2026

ASD-STE100 Simplified Technical English rules, repurposed as a Claude Code skill for rewriting ambiguous agent-facing English.

Python 6,804 391 Updated Nov 20, 2026

LeaderWorkerSet & DisaggregatedSet: Kubernetes APIs for Distributed and Disaggregated AI Serving

Go 910 214 Updated Nov 21, 2026
Python 146 79 Updated Nov 22, 2026

Optimize prompts, code, and more with AI-powered Reflective Optimization

Jupyter Notebook 7,530 631 Updated Nov 21, 2026

Lightweight coding agent that runs in your terminal

Rust 136,090 21,586 Updated Nov 22, 2026

High Performance Serving Runtime For Interactive Super Intelligence System

Python 1,896 783 Updated Nov 22, 2026

AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.

Python 900 274 Updated Nov 20, 2026

llm-d Router: The intelligent entry point for inference requests

Go 476 563 Updated Nov 21, 2026

《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

Python 59,024 6,929 Updated Nov 22, 2026

Dooly is a configuration agnostic, redundancy aware profiling method for LLM inference downstream tasks. Doolyprof automatically collects the set of unique operations called by your deployment conf…

Python 16 2 Updated Nov 21, 2026
C++ 194 57 Updated Nov 21, 2026

vLLM wall-clock emulation pluging to allow running the real vllm serve and benchmark without gpu with simple mocking

Python 17 1 Updated Aug 21, 2026

Speed of Light Analysis for ML Model Runtime

Python 147 30 Updated Nov 22, 2026

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。

1,663 276 Updated Apr 17, 2026

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

Python 1,851 138 Updated Aug 21, 2026

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

Shell 329,928 27,729 Updated Nov 19, 2026

[CVPR 2025] A Hierarchical Movie Level Dataset for Long Video Generation

Python 104 3 Updated Mar 16, 2025

[CVPR 2026] ViStoryBench: AI Story Visualization Benchmark

Python 173 11 Updated May 10, 2026

Open Source AI Accelerator Research Platform Standard / 开源推理研究平台

Python 2,075 386 Updated Nov 22, 2026

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

Cuda 2,624 277 Updated Nov 22, 2026

Moving to vllm-project/vllm-jax. TPU inference for vLLM, with unified JAX and PyTorch support.

Python 481 363 Updated Nov 22, 2026

Adaptive Experimentation Platform

Python 2,848 393 Updated Nov 17, 2026

Incubating P/D sidecar for llm-d

Go 17 36 Updated Nov 13, 2025
Next
0