ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-05-01 03:41:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use fused gemv+add only for TG (#933)

Browse Source 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-11-10 08:34:24 +02:00
committed by GitHub
parent 56ee303254
commit bf474e9bff
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-cuda.cu
View File

@@ -2067,7 +2067,7 @@ static int ggml_cuda_mul_mat_q(ggml_backend_cuda_context & ctx, const ggml_tenso
auto stream = ctx.stream(); auto stream = ctx.stream();
auto fusion = ctx.fusion; auto fusion = ctx.fusion && src1->ne[1] == 1;
auto ne10_padded = GGML_PAD(src1->ne[0], MATRIX_ROW_PADDING); auto ne10_padded = GGML_PAD(src1->ne[0], MATRIX_ROW_PADDING);
auto nb10_padded = ne10_padded*sizeof(block_q8_1)/QK8_1; auto nb10_padded = ne10_padded*sizeof(block_q8_1)/QK8_1;