Ruben Ortlam 25a1d63f43 vulkan: use flops instead of weight tensor size for submission heuristic (#25005) ...

* vulkan: extract flops calculation into function

* use flops instead of matmul src0 tensor size for submission threshold

* use unsigned ints

2026-06-29 15:24:44 +02:00

..

cmake

ggml : Parallelize quant LUT init (#23595)

2026-05-25 10:15:46 +03:00

include

sycl : support --split-mode tensor (#24152)

2026-06-25 08:35:21 +03:00

src

vulkan: use flops instead of weight tensor size for submission heuristic (#25005)

2026-06-29 15:24:44 +02:00

.gitignore

…

CMakeLists.txt

ggml : bump version to 0.15.3 (ggml/1550)

2026-06-26 15:04:42 +03:00