Measured runtime tuning for ComfyUI: per-architecture kernel selection, int8 linear tiles, butterfly convrot rotation, attention kernels (gfx906 first-class)
What is the LaoBro/ComfyUI-GPU-Tuning GitHub project? Description: "Measured runtime tuning for ComfyUI: per-architecture kernel selection, int8 linear tiles, butterfly convrot rotation, attention kernels (gfx906 first-class)". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.
Question is copied to clipboard — paste it after the AI opens.
Add it to a GitHub README or profile — the card updates as the ranking changes:
Clone via HTTPS
Clone via SSH
Download ZIP
Download master.zipReport bugs or request features on the ComfyUI-GPU-Tuning issue tracker:
Open GitHub Issues