Max Krasnyansky 9e96d390f7 hexagon: dma optimizations (mostly fixing regressions) (llama/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

2026-04-30 11:28:56 +03:00

..

cmake

cmake : remove unused file (ggml/1419)

2026-02-08 09:29:10 +02:00

include

llama: fix llama-model-saver (llama/20503)

2026-03-29 15:04:36 +03:00

src

hexagon: dma optimizations (mostly fixing regressions) (llama/21137)

2026-04-30 11:28:56 +03:00

.gitignore

…

CMakeLists.txt

ggml : bump version to 0.9.9 (ggml/1449)

2026-04-30 11:28:52 +03:00