public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Corrected: changed s13 = src1->nb[3] instead of nb[2] (llama/18724)

This commit is contained in:
Michael Wand 2026-01-10 01:16:07 -08:00 committed by Georgi Gerganov
parent 4af27bf2da
commit 45be2cd27a
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.cu
View File

@ -190,7 +190,7 @@ void ggml_cuda_mul_mat_q(
{
const int64_t s11 = src1->nb[1] / ts_src1;
const int64_t s12 = src1->nb[2] / ts_src1;
const int64_t s13 = src1->nb[2] / ts_src1;
const int64_t s13 = src1->nb[3] / ts_src1;
if (use_native_mxfp4) {
quantize_mmq_mxfp4_cuda(src1_d, ids_src1.get(), src1_q8_1.get(), src0->type, ne10, s11, s12, s13,