Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-19 17:24:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

sycl: cap non-contiguous concat block at ne0

Browse Source
This commit is contained in:
Simon Gardling
2026-07-19 14:38:02 -04:00
parent dcc5f72053
commit e792674540
1 changed files with 8 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-sycl/concat.cpp
+8 -1
View File
@@ -127,7 +127,14 @@ static void concat_T_sycl_non_cont(
int64_t ne2, int64_t ne3, uint64_t nb0, uint64_t nb1, uint64_t nb2,
uint64_t nb3, int32_t dim) {
sycl::range<3> gridDim(ne3, ne2, ne1);
sycl::range<3> blockDim(1, 1, SYCL_CONCAT_BLOCK_SIZE);
// Avoid oversubscribing device when there is not enough elements along the innermost dim to
// fill a full SYCL_CONCAT_BLOCK_SIZE. For larger # of elements, the full SYCL_CONCAT_BLOCK_SIZE
// is used.
const int64_t ne0_pad = GGML_PAD(ne0, WARP_SIZE);
const int64_t block_ne0 = ne0_pad < SYCL_CONCAT_BLOCK_SIZE ? ne0_pad : (int64_t) SYCL_CONCAT_BLOCK_SIZE;
sycl::range<3> blockDim(1, 1, block_ne0);
stream->parallel_for(sycl::nd_range<3>(gridDim * blockDim, blockDim), [=](sycl::nd_item<3> item_ct1) {
int64_t i3 = item_ct1.get_group(0);
int64_t i2 = item_ct1.get_group(1);