]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 3d032ec)
embedding : adjust `n_ubatch` value (#6296)
authorMinsoo Cheong <redacted>
Tue, 26 Mar 2024 09:11:46 +0000 (18:11 +0900)
committerGitHub <redacted>
Tue, 26 Mar 2024 09:11:46 +0000 (11:11 +0200)
commitdeb7240100da99555b9ab9dc635021e591fceaf5
tree5dbdda5c6aca9150437dd6d6031b657156d958c2tree
parent3d032ece8e6973441273601ca2981130608e287dcommit | diff
embedding : adjust `n_ubatch` value (#6296)

* embedding: assign `n_ubatch` value, print error on `n_batch` overflow

* Update examples/embedding/embedding.cpp

Co-authored-by: Xuan Son Nguyen <redacted>
* use %ld instead of %lld

* Revert "use %ld instead of %lld"

This reverts commit ea753ede90a86a0699f65878cc8e2020ff5eabb8.

---------

Co-authored-by: Xuan Son Nguyen <redacted>
examples/embedding/embedding.cpp diff | blob | history
Packaging of ggml-org/llama.cpp