tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 04:35:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-cpu: support IQ4_NL_4_4 by runtime repack (#10541)

Browse Source 
* ggml-cpu: support IQ4_NL_4_4 by runtime repack

* ggml-cpu: add __ARM_FEATURE_DOTPROD guard
This commit is contained in:
Shupei Fan
2024-11-28 20:52:03 +08:00
committed by GitHub
parent 2025fa67e9
commit c202cef168
8 changed files with 352 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@ -91,6 +91,7 @@ extern "C" {
GGML_BACKEND_API int ggml_cpu_has_neon (void);
GGML_BACKEND_API int ggml_cpu_has_arm_fma (void);
GGML_BACKEND_API int ggml_cpu_has_fp16_va (void);
GGML_BACKEND_API int ggml_cpu_has_dotprod (void);
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