root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 03:14:35 +00:00
Code Issues Actions 7 Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Johannes Gäßler 2024-06-27 16:26:05 +02:00 committed by GitHub
parent f675b20a3b
commit 85a267daaa
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/mmq.cuh
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); 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); ggml_cuda_pool_alloc<float> tmp_fixup(pool, block_nums_mmq.x * mmq_x*mmq_y);
if (args.ne01 % mmq_y == 0) { if (args.ne01 % mmq_y == 0) {