tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-02 15:55:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-cpu: Add CPU backend support for KleidiAI library (#11390)

Browse Source 
* ggml-cpu: Add CPU backend support for KleidiAI library

* Add environmental variable GGML_KLEIDIAI_SME

* Add support for multithread LHS conversion

* Switch kernel selection order to dotprod and i8mm

* updates for review comments

* More updates for review comments

* Reorganize and rename KleidiAI files

* Move ggml-cpu-traits.h to source file

* Update cmake for SME build and add alignment for SME

* Remove append GGML_USE_CPU_KLEIDIAI to the GGML_CDEF_PUBLIC list
This commit is contained in:
Charles Xu
2025-02-20 14:06:51 +01:00
committed by GitHub
parent 4806498bf1
commit c5d91a7400
9 changed files with 767 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/include/ggml-cpu.h
View File

@ -95,6 +95,7 @@ extern "C" {
GGML_BACKEND_API int ggml_cpu_has_matmul_int8(void);
GGML_BACKEND_API int ggml_cpu_has_sve (void);
GGML_BACKEND_API int ggml_cpu_get_sve_cnt (void); // sve vector length in bytes
GGML_BACKEND_API int ggml_cpu_has_sme (void);
// other
GGML_BACKEND_API int ggml_cpu_has_riscv_v (void);
GGML_BACKEND_API int ggml_cpu_has_vsx (void);