public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-06 06:21:41 +02:00
Code Issues Packages Projects Releases Wiki Activity

ggml-zendnn : add ZenDNN backend for AMD CPUs (llama/17690)

Browse Source 
* ggml-zennn: add ZenDNN backend support

* ggml-zendnn : address ZenDNN backend review fixes and suggestions

* docs : apply blockquote syntax to ZenDNN docs

---------

Co-authored-by: Manoj Kumar <mkumar@zettabolt.com>
This commit is contained in:
Vishal Singh
2025-12-12 17:53:21 +02:00
committed by Georgi Gerganov
co-authored by Manoj Kumar
parent c5e1807071
commit ebff8f9db9
6 changed files with 593 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-backend-reg.cpp
+8
View File
@@ -73,6 +73,10 @@
#include "ggml-cann.h"
#endif
#ifdef GGML_USE_ZENDNN
#include "ggml-zendnn.h"
#endif
// disable C++17 deprecation warning for std::codecvt_utf8
#if defined(__clang__)
# pragma clang diagnostic push
@@ -203,6 +207,9 @@ struct ggml_backend_registry {
#ifdef GGML_USE_OPENCL
register_backend(ggml_backend_opencl_reg());
#endif
#ifdef GGML_USE_ZENDNN
register_backend(ggml_backend_zendnn_reg());
#endif
#ifdef GGML_USE_HEXAGON
register_backend(ggml_backend_hexagon_reg());
#endif
@@ -605,6 +612,7 @@ void ggml_backend_load_all_from_path(const char * dir_path) {
#endif
ggml_backend_load_best("blas", silent, dir_path);
ggml_backend_load_best("zendnn", silent, dir_path);
ggml_backend_load_best("cann", silent, dir_path);
ggml_backend_load_best("cuda", silent, dir_path);
ggml_backend_load_best("hip", silent, dir_path);