Titaniumtown 6c8dcaa7ae sycl: parallelize the non-contiguous concat kernel (#25852) ...

* sycl: parallelize the non-contiguous concat kernel

Launch geometry only: the non-contiguous concat kernel launched a single-lane
work-group (1, 1, 1), now it will launch a (1, 1, SYCL_CONCAT_BLOCK_SIZE) one.

SYCL_CONCAT_BLOCK_SIZE is defined in `ggml/src/ggml-sycl/presets.hpp`.

llama-bench (Arc Pro B70, Qwen3.6-27B-UD-Q4_K_XL, -fa on, q8_0 KV),
on top of upstream master: pp2048 920 -> 1006 t/s (+9.4%)

* sycl: cap non-contiguous concat block at ne0

* sycl: make non-contiguous concat block width env-tunable (GGML_SYCL_CONCAT_BLOCK_SIZE)

* Revert "sycl: make non-contiguous concat block width env-tunable (GGML_SYCL_CONCAT_BLOCK_SIZE)"

This reverts commit 2709909e79.

2026-08-04 10:08:05 +08:00

..

cmake

ggml : Parallelize quant LUT init (#23595)

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

include

RPC: add tensor_memset (#25912)

2026-07-29 15:04:30 +08:00

src

sycl: parallelize the non-contiguous concat kernel (#25852)

2026-08-04 10:08:05 +08:00

.gitignore

vulkan : cmake integration (#8119)

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

CMakeLists.txt

ggml : bump version to 0.18.0 (ggml/1576)

2026-07-30 15:44:24 +03:00