backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels (llama/9921)

* backend-cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
This commit is contained in:
Charles Xu
2024-11-20 21:00:08 +02:00
committed by Georgi Gerganov
co-authored by Diego Devesa
parent 746bf2596f
commit 3298916e5e
7 changed files with 268 additions and 21 deletions
+3
View File
@@ -169,6 +169,9 @@ extern "C" {
GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_cpu_hbm_buffer_type(void);
#endif
GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_cpu_aarch64_buffer_type(void);
GGML_BACKEND_API bool ggml_backend_cpu_buft_is_aarch64(ggml_backend_buffer_type_t buft);
#ifdef __cplusplus
}
#endif