CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix GGML_F32Cx8_STORE in AVX without F16C path (#619)

Browse Source
This commit is contained in:
slaren
2023-03-30 11:16:30 +02:00
committed by GitHub
parent 9cbc404ba6
commit ed3c680bcd
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml.c
View File

@@ -1297,7 +1297,7 @@ static inline void __avx_f32cx8_store(ggml_fp16_t *x, __m256 y) {
_mm256_storeu_ps(arr, y);
for (int i = 0; i < 8; i++)
x[i] = GGML_FP16_TO_FP32(arr[i]);
x[i] = GGML_FP32_TO_FP16(arr[i]);
}
#define GGML_F32Cx8_LOAD(x) __avx_f32cx8_load(x)
#define GGML_F32Cx8_STORE(x, y) __avx_f32cx8_store(x, y)