gfx906
Here are 7 public repositories matching this topic...
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.
-
Updated
Apr 22, 2026 - Python
Open-source local AI server configs, GFX906 runtime maintenance, reproducible benchmarks, and QC methods for affordable AI research infrastructure.
-
Updated
Jun 23, 2026 - Shell
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.
-
Updated
May 8, 2026 - Python
Benchmarks and runnable setup for Qwen LLMs on AMD Radeon VII (gfx906) via llama.cpp + ROCm in Docker
-
Updated
May 4, 2026 - Shell
ROCm/Unsloth/bitsandbytes 4-bit lab and VRAM benchmarks for AMD MI50/gfx906 LLM fine-tuning
-
Updated
Jun 3, 2026 - Python
Improve this page
Add a description, image, and links to the gfx906 topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the gfx906 topic, visit your repo's landing page and select "manage topics."