sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-15 13:34:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

opencl: fix crash when warming up MoE on Adreno (#22876)

Browse Source
This commit is contained in:
lhez
2026-05-13 11:24:33 -07:00
committed by GitHub
parent 527045bfb0
commit 1e4579fbb8
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-opencl/ggml-opencl.cpp
View File

@@ -13132,7 +13132,7 @@ static void moe_router_reoerder(ggml_backend_t backend, const ggml_tensor * src,
CL_CHECK(clSetKernelArg(kernel, 4, sizeof(int), &ne02));
size_t histogram_global_size[] = {(size_t)(((ne21 + 63) / 64) * 64), static_cast<size_t>(ne20), 1};
size_t histogram_local_size[] = {64, static_cast<size_t>(ne20), 1};
size_t histogram_local_size[] = {64, 1, 1};
backend_ctx->enqueue_ndrange_kernel(kernel, 3, histogram_global_size, histogram_local_size, src);
// Scan