happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
llama.cpp/ggml/src/ggml-hexagon
History
l3utterfly 6db3d1ffe6
ggml-hexagon: graceful fallback for older socs where rpcmem_alloc2 and FASTRPC_GET_URI is unsupported (#16987) 
* support older socs where FASTRPC_GET_URI is unsupported

* added graceful fallback when FASTRPC_GET_URI call fails

* use weak symbols instead of loading libcdsprpc.so dynamically

* Add weak pragma for rpcmem_alloc2

* Remove weak declaration for rpcmem_alloc2 in ggml-hexagon.cpp

Removed weak declaration for rpcmem_alloc2.

* Enforce ndev to 1 for archs below v75

Force ndev to 1 for SoCs architectures lower than v75.
 		2025-11-05 21:46:38 -08:00
..
htp refactor: replace sprintf with snprintf for safer string handling in dump functions (#16913) 2025-11-04 12:25:39 -08:00
CMakeLists.txt Add experimental ggml-hexagon backend for the Hexagon NPU (#16547) 2025-10-22 13:47:09 -07:00
ggml-hexagon.cpp ggml-hexagon: graceful fallback for older socs where rpcmem_alloc2 and FASTRPC_GET_URI is unsupported (#16987) 2025-11-05 21:46:38 -08:00
htp-utils.c Add experimental ggml-hexagon backend for the Hexagon NPU (#16547) 2025-10-22 13:47:09 -07:00
htp-utils.h ggml-hexagon: graceful fallback for older socs where rpcmem_alloc2 and FASTRPC_GET_URI is unsupported (#16987) 2025-11-05 21:46:38 -08:00