]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 203b7f1)
ggml: add support for float16 input tensors in pooling operations (ggml/895)
authorIvan Filipov <redacted>
Mon, 22 Jul 2024 11:32:02 +0000 (14:32 +0300)
committerGeorgi Gerganov <redacted>
Sat, 27 Jul 2024 14:43:44 +0000 (17:43 +0300)
commit9f77d899b7b0d56496f679e54b797da6199fed8e
tree5d91c1b74dcf1eb6ebe540cdf2d0bcfd23a4badetree
parent203b7f1531303a060730ec1d1e01920e70302398commit | diff
ggml: add support for float16 input tensors in pooling operations (ggml/895)

* Add support for float16 tensors in 1d pooling operations

* Add support for float16 input tensors in 2d pooling operations

* code cleanup

remove unnecessary casting during srow ptr initialization

---------

Co-authored-by: vanaka11 <redacted>
ggml/src/ggml.c diff | blob | history
Packaging of ggml-org/llama.cpp