]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 8a4441e)
server : ensure batches are either all embed or all completion (#8420)
authorDouglas Hanley <redacted>
Fri, 12 Jul 2024 08:14:12 +0000 (03:14 -0500)
committerGitHub <redacted>
Fri, 12 Jul 2024 08:14:12 +0000 (11:14 +0300)
commitc3ebcfa148e867a68e78fd5c4f0c23e8f84c788b
treebc283ee746701212132ffc5cb8d9008bdb010995tree
parent8a4441ea1a2564578134404f31158c318e9c0bf3commit | diff
server : ensure batches are either all embed or all completion (#8420)

* make sure batches are all embed or all non-embed

* non-embedding batch for sampled tokens; fix unused params warning
examples/server/server.cpp diff | blob | history
Packaging of ggml-org/llama.cpp