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

cmake: Added more x86_64 CPU backends when building with GGML_CPU_ALL_VARIANTS=On (#18186)

Browse Source 
* minor: Consolidated `#include <immintrin.h>` under `ggml-cpu-impl.h`

* cmake: Added more x86-64 CPU backends when building with `GGML_CPU_ALL_VARIANTS=On`

- `ivybridge`
- `piledriver`
- `cannonlake`
- `cascadelake`
- `cooperlake`
- `zen4`

Resolves: #17966
This commit is contained in:
Boian Berberov
2025-12-28 07:33:29 +00:00
committed by GitHub
parent 4fd59e8427
commit 94de74e7b1
5 changed files with 34 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cpu/ggml-cpu-impl.h
+1 -1
View File
@@ -328,7 +328,7 @@ inline static int32x4_t ggml_vdotq_s32(int32x4_t acc, int8x16_t a, int8x16_t b)
#if defined(_MSC_VER) || defined(__MINGW32__)
#include <intrin.h>
#elif defined(__AVX__) || defined(__AVX2__) || defined(__AVX512F__) || defined(__SSSE3__) || defined(__SSE3__) || defined(__SSE__)
#elif defined(__SSE__) || defined(__SSE3__) || defined(__SSSE3__) || defined(__AVX__) || defined(__F16C__) || defined(__AVX2__) || defined(__AVX512F__) || defined(__AVX512BF16__)
#include <immintrin.h>
#endif