TitaniumtownandGitHub f275595dd1 sycl: fix thread/block count in quantized cpy kernel launches (#27160) ...

Adjusts the thread/block count to be proportional to the size
of the quant, reducing under/over subscription.

Largest perf improvement is the q4_0 -> f32 path, with, on
a Arc 70, throughput goes from 20.21 GB/s to 158.19 GB/s

The rest of the quants are flat in performance uplift.

2026-08-17 07:32:16 +03:00

..

cmake

cmake : add config version support (ggml/1582)

2026-08-12 14:23:43 +03:00

include

ggml : recurrent state rollback for ggml_ssm_scan (#26623)

2026-08-14 17:20:40 +03:00

src

sycl: fix thread/block count in quantized cpy kernel launches (#27160)

2026-08-17 07:32:16 +03:00

.gitignore

vulkan : cmake integration (#8119)

2024-07-13 18:12:39 +02:00

CMakeLists.txt

ggml : bump version to 0.20.0 (ggml/1584)

2026-08-14 19:06:19 +03:00