public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-06 06:21:41 +02:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: fix MMQ stream-k for --split-mode row (llama/8167)

Browse Source
This commit is contained in:
Johannes Gäßler
2024-07-08 14:53:55 +03:00
committed by Georgi Gerganov
parent 3eea171cab
commit bf88c94da9
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/mmq.cuh
+1 -1
View File
@@ -2475,7 +2475,7 @@ static void launch_mul_mat_q(ggml_backend_cuda_context & ctx, const mmq_args & a
const dim3 block_nums_mmq(nsm, 1, 1);
ggml_cuda_pool & pool = ctx.pool();
ggml_cuda_pool & pool = ctx.pool(id);
ggml_cuda_pool_alloc<float> tmp_fixup(pool, block_nums_mmq.x * mmq_x*mmq_y);
if (args.ne01 % mmq_y == 0) {