Update: llama.cpp for Radeon VII / MI50 / MI60 — +14% PP, +9% long-context fill vs upstream + adaptive Flash Attention

I posted a new gfx906 based llama.cpp fork a few days ago. One of the main points of critique was that i did not provide sufficient numbers for the gains to be achieved. -- TL;DR: After switching our Qwen 3.8 27B production setup to DFlash2, several of the old gfx906 optimizations turned out to be neutral or outright regressions. We went back through the existing gfx906 work, isolated the problem areas, reworked the small-Q Flash Attention path and added adaptive native/convert selection. Against current llama.cpp mainline, the resulting fork is now +14.1% in first-batch PP (379.2 vs 332.3 t/s) and +9.3% in 120k-context fill (252.6 vs 231.1 t/s) , while deep-context TG is effectively tied at 13.6 vs 13.5 t/s . DFlash acceptance is identical at 0.691 , and deterministic output matches byte-for-byte. --- Our thread is here: forum.level1techs.com/t/glm-and-i-creat...-mi50-mi60-radeon-vii-gcn-hip/254257/3 This is the github for it: github.com/milpster/gfx906-llama-cpp