hrx

HRX, LOOM, Mac, and AMD running top speed kernels with a self optimizing engine.

1bit engine: local LLM inference for AMD Ryzen AI (Strix Halo) inside Lemonade. HRX with our Loom kernels on the Radeon iGPU, plus the XDNA 2 NPU; OpenAI-compatible API. Runs Qwen3.8, Zyphra ZAYA1, ternary Bonsai.

MiniMax H3 video and audio generation on AMD Strix Halo, powered by Loom and HRX.

HRX parser for Elixir

A GPU-powered vector database for unified-memory systems, built on HRX and Loom. Exact search and custom GPU scoring on AMD Strix Halo.

A Haskell implementation of Google's HRX archive format

ArcFace face embeddings in Rust with HRX and Loom kernels for AMD gfx1151.

SCRFD face detection in Rust for AMD GPUs.

DINOv3 ViT-S+/16 inference in Rust for AMD GPUs with HRX and Loom

Lightweight GPU and NPU compute from Rust with Loom and HRX

Krea 2 image generation on AMD Strix Halo, powered by Loom kernels and HRX