hec-ovi/llama-vulkan-strix

This repository builds llama.cpp for Strix Halo devices.

Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; portable dir, Docker, and distrobox.

SGLang Docker image for AMD Strix Halo (gfx1151 / Radeon 8060S)

LLM inference in C/C++

A high-throughput and memory-efficient inference and serving engine for LLMs - Optimized for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60

llama.cpp modified to work with Strix Halo + dGPU as an accelerator, Dual Strix Halo Machines, or both

Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.

Reproducible, evidence-backed llama.cpp serving recipes for Strix Halo class machines — annotated parameters, ▏ multi-witness results, agent-first tooling.