]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: c14f72d)
sync : ggml (#5633)
authorGeorgi Gerganov <redacted>
Wed, 21 Feb 2024 14:17:10 +0000 (16:17 +0200)
committerGitHub <redacted>
Wed, 21 Feb 2024 14:17:10 +0000 (16:17 +0200)
commiteccd7a26ddbff19e4b8805648f5f14c501957859
tree8b16c79a208cfc72f1cc7d696925a6431957fe77tree
parentc14f72db9c62d71d35eb1c141745c0bd0cb27b49commit | diff
sync : ggml (#5633)

* ggml : fix conv_2d batch mode (ggml/737)

Co-authored-by: bssrdf <redacted>
* ggml : compute forward no longer pass src tensors (ggml/729)

* sync : ggml

ggml-ci

---------

Co-authored-by: bssrdf <redacted>
Co-authored-by: bssrdf <redacted>
ggml.c diff | blob | history
scripts/sync-ggml.last diff | blob | history
Packaging of ggml-org/llama.cpp