wylab/llama.cpp
0
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-14 18:02:52 +02:00
Code Issues Packages Projects Releases Wiki Activity

ggml-cpu: temporarily add #28775 patch until its merged

Browse Source 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
This commit is contained in:
Aaron Teo
2026-09-13 21:53:44 +08:00
parent 838329ee0e
commit d4645257b6
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cpu/arch/s390/repack.cpp
+2
View File
@@ -70,6 +70,7 @@ void ggml_quantize_mat_q8_0_4x4(const float * GGML_RESTRICT x, void * GGML_RESTR
#endif
}
#if defined(__VXE__) || defined(__VXE2__)
static inline int16x8_t vxe_dot_acc(const int8x16_t v_x, const int8x16_t v_y, const int16x8_t v_acc) {
return vec_meadd(v_x, v_y, vec_moadd(v_x, v_y, v_acc));
}
@@ -84,6 +85,7 @@ static inline int32x4_t vxe_fold(const int16x8_t v_sumi) {
const int16x8_t v_ones = vec_splats((int16_t)1);
return vec_add(vec_mule(v_sumi, v_ones), vec_mulo(v_sumi, v_ones));
}
#endif
void ggml_gemv_q4_0_4x4_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, const void * GGML_RESTRICT vy, int nr, int nc) {
const int qk = QK8_0;