Highlights
- Pro
Stars
Formal verification workflow and skill stack for coding agents (TLA+, Z3, Apalache, TLAPS)
A PyTorch native automated mega-kernel compiler
Let AI use your iPhone or Android phone, with you in the loop: any MCP agent from macOS, Windows or Linux, or Pinky itself, right on the phone.
Make humans and AI agents work as one team — open-source and self-hostable.
OpenAgents - The collaboration OS for AI agents
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Mac.apk: Run Android apps natively on Apple Silicon Macs
让 Codex 通过 USB 操作真实 iPhone:引导安装、App 自动化、实时屏幕与截图回退。
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
Lightweight Benchmark Server for Agentic GPU Programming
A model-agnostic GPU runtime for shipping models as verified programs.
Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.
A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.
MAGI-2-preview: Scaling Video Generation Models Efficiently
Breakable CUDA graph capture for PyTorch - capture compatible regions as CUDA graphs while running incompatible operations eagerly between them.
MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts
A tutorial on modern GPU programming for machine learning systems
SGLang-native serving for the Moet sign-symmetric W2 expert format with SM120 W2/W4 kernels, GLM-5.2 NVFP4 TP4 on 4x RTX PRO 6000
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.
A compiler, optimizer and executor for financial expressions and factors
Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.