]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 674804a)
[CANN] Adapt to dynamically loadable backends mechanism (#9970)
authorleo-pony <redacted>
Tue, 22 Oct 2024 08:16:01 +0000 (16:16 +0800)
committerGitHub <redacted>
Tue, 22 Oct 2024 08:16:01 +0000 (16:16 +0800)
commit6b8447352df3d662b56280c8fc38d7f092885787
tree954f466b0378d6bd25c22216bdff73800b852357tree
parent674804a99617b4f90292b4080ecab450ea3d30bacommit | diff
[CANN] Adapt to dynamically loadable backends mechanism (#9970)

* [CANN] Adapt to dynamically loadable backends mechanism

* Fix the Bug: inference running result is garbled in debug running model for LM models who's type is Q4_0 class

* Handle the review comments of this pull request
ggml/include/ggml-cann.h diff | blob | history
ggml/src/ggml-backend.cpp diff | blob | history
ggml/src/ggml-cann.cpp diff | blob | history
src/llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp