ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-23 22:54:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix MMQ when running with quantized K cache without FA

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-08-08 13:42:03 +03:00
parent 0dce7f9128
commit f747cbca08
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/mmq.cu
View File

@@ -14,7 +14,7 @@ void ggml_cuda_op_mul_mat_q(
const int64_t src1_padded_row_size, cudaStream_t stream) {
const int64_t ne00 = src0->ne[0];
const int64_t nb01 = src0->nb[1];
const int64_t nb01 = ggml_row_size(src0->type, ne00);
const int64_t ne10 = src1->ne[0];
const int64_t ne11 = src1->ne[1];