vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : fix arch check in bf16_to_fp32

Browse source
This commit is contained in:
slaren 2024-11-04 13:24:47 +01:00
parent ea02c753eb
commit 1ba978549d
1 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/src/ggml.c
View file

@ -392,6 +392,8 @@ void ggml_bf16_to_fp32_row(const ggml_bf16_t * x, float * y, int64_t n) {
16))); 16)));
} }
} }
#endif
#if defined(__AVX2__)
if (ggml_cpu_has_avx2()) { if (ggml_cpu_has_avx2()) {
for (; i + 8 <= n; i += 8) { for (; i + 8 <= n; i += 8) {
_mm256_storeu_ps(y + i, _mm256_storeu_ps(y + i,