]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 4fd59e8)
cmake: Added more x86_64 CPU backends when building with `GGML_CPU_ALL_VARIANTS=On...
authorBoian Berberov <redacted>
Sun, 28 Dec 2025 07:33:29 +0000 (07:33 +0000)
committerGitHub <redacted>
Sun, 28 Dec 2025 07:33:29 +0000 (09:33 +0200)
commit94de74e7b1b9ee6404b54ebb0df273a3ef35a555
tree141544616dd1bec8dafc165235c15d82aa735f78tree
parent4fd59e8427e78241b01b1db352ef28be6bf304fdcommit | diff
cmake: Added more x86_64 CPU backends when building with `GGML_CPU_ALL_VARIANTS=On` (#18186)

* 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
ggml/CMakeLists.txt diff | blob | history
ggml/src/CMakeLists.txt diff | blob | history
ggml/src/ggml-cpu/ggml-cpu-impl.h diff | blob | history
ggml/src/ggml-cpu/simd-mappings.h diff | blob | history
ggml/src/ggml-impl.h diff | blob | history
Packaging of ggml-org/llama.cpp