]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: a5e4759)
CANN: Support Ascend310P to accelerate F32 and F16 Model (#10216)
authorleo-pony <redacted>
Fri, 22 Nov 2024 06:07:20 +0000 (14:07 +0800)
committerGitHub <redacted>
Fri, 22 Nov 2024 06:07:20 +0000 (14:07 +0800)
commitc18610b4ee29ca056bb4f2d375a4ad1b16f44ef7
tree7a8bbc0acf63e29eb56575a3a7b5c0fdd6ef4215tree
parenta5e47592b6171ae21f3eaa1aba6fb2b707875063commit | diff
CANN: Support Ascend310P to accelerate F32 and F16 Model (#10216)

* CANN Support Ascend310P to accelerate F32 and F16 Model

* Add compile option soc type macro ASCEND_310P to ggml-cann lib

* Remove unused code

* Remove the ascend soc_type hard code compile option in CMakelist.txt
ggml/src/ggml-cann/CMakeLists.txt diff | blob | history
ggml/src/ggml-cann/aclnn_ops.cpp diff | blob | history
ggml/src/ggml-cann/kernels/CMakeLists.txt diff | blob | history
ggml/src/ggml-cann/kernels/dup.cpp diff | blob | history
ggml/src/ggml-cann/kernels/get_row_f16.cpp diff | blob | history
ggml/src/ggml-cann/kernels/get_row_f32.cpp diff | blob | history
ggml/src/ggml-cann/kernels/get_row_q4_0.cpp diff | blob | history
Packaging of ggml-org/llama.cpp