sleepy/llama.cpp
1
0
Fork 0
Code Issues 16 Pull Requests Actions 34 Packages Projects Releases Wiki Activity

ggml : LoongArch fixes (#16958)

Browse Source 
* Fix test-quantize-fns f16 and q4_0 failed when use LSX

* Fix LoongArch set float intrinsic when use LSX/LASX
This commit is contained in:
Jinyang He
2025-11-03 14:40:02 +08:00
committed by GitHub
parent ee3a5a10ad
commit fcfce040e8
3 changed files with 32 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cpu/ggml-cpu-impl.h
+3 -1
View File
@@ -500,13 +500,15 @@ inline static int32x4_t ggml_vec_dot(int32x4_t acc, int8x16_t a, int8x16_t b) {
#endif
#if defined(__loongarch_asx)
#if defined(__loongarch_sx)
/* float type data load instructions */
static __m128 __lsx_vreplfr2vr_s(const float val) {
v4f32 res = {val, val, val, val};
return (__m128)res;
}
#endif
#if defined(__loongarch_asx)
static __m256 __lasx_xvreplfr2vr_s(const float val) {
v8f32 res = {val, val, val, val, val, val, val, val};
return (__m256)res;