happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

ggml-cpu: fix incorrect kval_mxfp4 type 

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
This commit is contained in:
Aaron Teo 2025-09-23 02:56:16 +08:00
parent 6549e3bcb7
commit 377d0fca3c
No known key found for this signature in database
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-cpu/arch/s390/quants.c
View File

@ -279,7 +279,7 @@ void ggml_vec_dot_mxfp4_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const vo
float sumf = 0.0f;
#if defined(__VXE__) || defined(__VXE2__)
const uint8x16_t v_k = vec_xl(0, kvalues_mxfp4);
const int8x16_t v_k = vec_xl(0, kvalues_mxfp4);
const uint8x16_t v_m = vec_splats((uint8_t)0x0F);
for (; ib + 1 < nb; ib += 2) {