]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 1db8c84)
speculative : fix handling of some input params (#9963)
authorGeorgi Gerganov <redacted>
Mon, 21 Oct 2024 06:37:12 +0000 (09:37 +0300)
committerGitHub <redacted>
Mon, 21 Oct 2024 06:37:12 +0000 (09:37 +0300)
commitbc219750845a59166d79f0d4ee3da1993b369b8a
tree9b267286bef25519d82a3938c80a9c092db1fb06tree
parent1db8c84fc62857e1e45c1c7ea93bcd5344cb3d31commit | diff
speculative : fix handling of some input params (#9963)

* speculative : fix batch sizes at initialization

ggml-ci

* speculative : handle params.n_predict == -1

* speculative : limit batch size to llama_n_batch
examples/speculative/speculative.cpp diff | blob | history
Packaging of ggml-org/llama.cpp