]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
overview / pkg / ggml / sources / ggml / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 1722262)
CANN: Improve the Inferencing Performance for Ascend NPU Device (llama/10454)
authorShanshan Shen <redacted>
Tue, 26 Nov 2024 10:08:37 +0000 (18:08 +0800)
committerGeorgi Gerganov <redacted>
Tue, 3 Dec 2024 19:05:37 +0000 (21:05 +0200)
commit1e1e78c05da5e8b4bed2bc037994deb5df156721
treec4896dec4f0a3e6e9bc8bd902ad83e0a72c5a58dtree
parent17222622b82efcbfb1723bec63cd4082cac92b47commit | diff
CANN: Improve the Inferencing Performance for Ascend NPU Device (llama/10454)

* improve inferencing performance for ascend npu.

Co-authored-by: Frank Mai <redacted>
* some modification after review

* some modifications after review

* restore some modifications

* restore some modifications

---------

Co-authored-by: shanshan shen <redacted>
Co-authored-by: Frank Mai <redacted>
src/ggml-cann/aclnn_ops.cpp diff | blob | history
src/ggml-cann/common.h diff | blob | history
src/ggml-cann/ggml-cann.cpp diff | blob | history
Packaging of ggml-org/ggml