]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 9d03d08)
llama : add function for model-based max number of graph nodes (#8622)
authorGeorgi Gerganov <redacted>
Sat, 27 Jul 2024 11:59:29 +0000 (14:59 +0300)
committerGitHub <redacted>
Sat, 27 Jul 2024 11:59:29 +0000 (14:59 +0300)
commit92090eca212650727e38b335c1d4accfbcc9b79c
treed62f4db42d9f7feb1902c2ed73cb46757e3968b0tree
parent9d03d085dd6cb275c078690bb64073b9b043e95fcommit | diff
llama : add function for model-based max number of graph nodes (#8622)

* llama : model-based max number of graph nodes

ggml-ci

* llama : disable 405B max_nodes path due to lack of complaints

ggml-ci
src/llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp