llama.cpp

f5d1c417 - hexagon: dma optimizations (mostly fixing regressions) (#21137)

hexagon: dma optimizations (mostly fixing regressions) (#21137) * hex-fa: add simple dma cache for Mask I noticed that we were refetch the mask rows over and over. This simple cache avoids that. * hex-dma: unset in-order desc bit which caused signficant perf regression We don't rely on true in order processing of the DMA descriptors anywhere. Turns out this mode caused significant regression of around 3-4 TPS during token gen. * hex-rope: update comment to clarify that we don't need in-order DMA completions