Stars
A lightweight data processing framework built on DuckDB and 3FS.
Turn your Android device into a powerful game streaming terminal! Gawr! ✨
Build an easy-to-use workflow for the next generation of video creation with agent
MLB-YouTube dataset, code and models for fine-grained activity recognition (CVsports 2018)
An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.
Run a virtual iPhone on an Apple Silicon Mac.
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Production-Grade Container Scheduling and Management
A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.
[EuroSys27] TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications
Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing,…
sgl-project / DeepGEMM
Forked from deepseek-ai/DeepGEMMDeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Flash-Muon: An Efficient Implementation of Muon Optimizer
Open Source AI Accelerator Research Platform Standard / 开源推理研究平台
AgentENV (AENV) is a distributed platform for running agent environments at scale.
Use Codex from Claude Code to review code or delegate tasks.
Build your agent from 200,000+ skills via skill RETRIEVAL & ORCHESTRATION
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
A simple, fast and robust program-aware agentic inference system.
[ACL 2026] Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization
[OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
A curated collection of papers and resources on On-Policy Distillation for Large Language Models.
Agent skill for long-form writing workbenches