CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : fix arch check in bf16_to_fp32 (#10164)

Browse Source
This commit is contained in:
Diego Devesa
2024-11-04 23:17:01 +01:00
committed by GitHub
parent 3407364776
commit a9e8a9a030
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

@@ -395,6 +395,8 @@ void ggml_bf16_to_fp32_row(const ggml_bf16_t * x, float * y, int64_t n) {
16)));
}
}
#endif
#if defined(__AVX2__)
if (ggml_cpu_has_avx2()) {
for (; i + 8 <= n; i += 8) {
_mm256_storeu_ps(y + i,