Stars
lithos-metal: high-performance LLM inference kernels and serving for Apple silicon.
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, and Pi. 44 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.
ripgrep recursively searches directories for a regex pattern while respecting your gitignore
B200 Attention from Scratch: understand one of the hardest GPU kernels on the latest hardware
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
Skills for Designers and Engineers.
A collection of GPU experiments and benchmarks for my personal understanding and research.
Mixture-of-experts (MoE) training megakernel for NVL72s
MSLK (Meta Superintelligence Labs Kernels) is a collection of PyTorch GPU operator libraries that are designed and optimized for GenAI training and inference, such as FP8 row-wise quantization and …
Master programming by recreating your favorite technologies from scratch.
A programmable tool and agent runtime for Pi
Production-ready MoE load balancing via real-time expert replication
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.
A tutorial on modern GPU programming for machine learning systems
FlyDSL is the Python front‑end of the project: a Flexible Layout Python DSL for expressing tiling, partitioning, data movement, and kernel structure at a high level.
Blackwell GEMM Kernel Optimization
C++ library for task-based, parallel programming on multi-core processors
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels