mi50

llama.cpp-gfx906

Open-source local AI server configs, GFX906 runtime maintenance, reproducible benchmarks, and QC methods for affordable AI research infrastructure.

FlashAttention-style custom attention backend for vLLM on AMD MI50/MI60/Radeon VII (gfx906). Downstream fork of mixa3607/ML-gfx906 with replacement HIP kernels and a vllm.general_plugins entry point.

Deploy Qwen3.6-27B GGUF on an AMD MI50 (gfx906) eGPU via vLLM + ROCm — docker-compose bundle with patches for Qwen3.5/3.6 hybrid Gated-DeltaNet support.

AMD Instinct MI50/MI60 (gfx906, HIP/ROCm) port of NInfer - the specialized single-GPU Qwen inference engine. First AMD target in the ecosystem. Audit complete, port in progress.

ROCm/Unsloth/bitsandbytes 4-bit lab and VRAM benchmarks for AMD MI50/gfx906 LLM fine-tuning

Local Paperless-ngx + Ollama integration for AI-based document titles, correspondents, document types, tags, review workflows, and backfill.

Run ComfyUI on AMD Radeon VII (gfx906) via Docker. ROCm 5.7 + PyTorch 2.3.1, SDXL 1024×1024 in ~28s/image. Pinned to ComfyUI v0.3.60 — the last gfx906-compatible build.