]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 58d07a8)
llama : expose llama_model_n_head_kv in the API (#11997)
authorVitali Lovich <redacted>
Tue, 25 Feb 2025 09:29:33 +0000 (01:29 -0800)
committerGitHub <redacted>
Tue, 25 Feb 2025 09:29:33 +0000 (11:29 +0200)
commit3e9a2860e996657fc10db8393cf65adc40703082
tree413c5c03e1d5b91f770f029dd10145946fcc2ce9tree
parent58d07a8043a1395177cf77b3e4f388e34182ae64commit | diff
llama : expose llama_model_n_head_kv in the API (#11997)

It's useful to be able to have this from the library layer as it's a key
parameter of the model (e.g. to figure out how much KV cache memory is
needed).
include/llama.h diff | blob | history
src/llama-model.cpp diff | blob | history
Packaging of ggml-org/llama.cpp