GitHub · C++
1bit-MONSTER/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.
- Stars
- 10
- Forks
- 2
- Stars gained in 24 hours
- +1
- Forks gained in 24 hours
- 0
Topics: amd, bitnet, gfx1151, gguf, hip, hrx, lemonade, linux, llama-cpp, llm
Latest data point: Nov 20, 2026 · 10 stars · 2 forks