Starred repositories
onnxruntime-qnn is the Qualcomm AI Runtime (QAIRT) execution provider for onnxruntime. It provides onnxruntime hardware acceleration and advanced functionalities on Qualcomm devices.
Beginner, advanced, expert level Rust training material
Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.
Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, and Vision fine-tuning — natively on MLX. Unsloth-compatible API.
OpenAI-compatible Endpoints to Serve Apple Fondation Model
https://gist.github.com/karpathy/8627fe009c40f57531cb18360106ce95 in many languages.
Office Compound Engineering plugin for Claude Code, Codex, and more
Exercises for Learning MLIR (Originally written for PPoPP 2026)
Helpful kernel tutorials and examples for tile-based GPU programming
An API-compatible, drop-in replacement for Apple's Foundation Models framework with support for custom language model providers.
AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming
Post-training with Tinker
A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …
Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild
A zero-dependency ML framework in C with a modern Python API for full control over execution and memory.
Hierarchical Reasoning Model Official Release
An extremely fast Python type checker and language server, written in Rust.
Artificial Neural Engine Machine Learning Library
Free, simple, fast interactive diagrams for any GitHub repository
Support PyTorch model conversion with LiteRT.