HRX, LOOM, Mac, and AMD running top speed kernels with a self optimizing engine.
One binary to rule them all: model-agnostic local LLM inference for AMD Strix Halo (Ryzen AI MAX+ 395) on Linux. Radeon 8060S iGPU (gfx1151) via HRX + our HIP kernels, XDNA 2 NPU via our NPU runtime, inside Lemonade Server with an OpenAI-compatible API. Qwen3.8, ZAYA1, BitNet b1.58, any GGUF. Apache-2.0.
MiniMax H3 video and audio generation on AMD Strix Halo, powered by Loom and HRX.
AMD GPU and NPU compute in Rust, with the Loom kernel compiler.
Krea 2 Turbo and Raw image generation on AMD Strix Halo. Built with Rust, HRX and Loom.
DINOv3 image embeddings and patch features on AMD Strix Halo. Built with Rust, HRX and Loom.
Cloudflare CLEF structured decisions from text, images and video on AMD Strix Halo. Rust, HRX and Loom.
Exact vector search and custom GPU scoring on AMD Strix Halo. Built with Rust, HRX and Loom.
ArcFace face alignment and embeddings on AMD Strix Halo. Built with Rust, HRX and Loom.
SCRFD face detection and landmarks on AMD Strix Halo. Built with Rust, HRX and Loom.
Source of https://1bit.gg/, docs and blog of the 1bit engine: model-agnostic local LLM inference on AMD Strix Halo (Ryzen AI MAX+ 395) inside Lemonade Server, on the Radeon 8060S iGPU via HRX and the XDNA 2 NPU. Apache-2.0.
To associate your repository with the hrx topic, visit your repo's landing page and select "manage topics."