]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: bb115d2)
graph : normalize Q, K, V shapes + sync cross attention (#12449)
authorGeorgi Gerganov <redacted>
Tue, 18 Mar 2025 19:35:19 +0000 (21:35 +0200)
committerGitHub <redacted>
Tue, 18 Mar 2025 19:35:19 +0000 (21:35 +0200)
commit75422e8bc42646005be0754f7aa438b97a5e777e
tree7f183926af7d84018a532c5469317a69f32c96catree
parentbb115d2bf7ed2cdd7dccd7ae74cc9cfe4b0adb71commit | diff
graph : normalize Q, K, V shapes + sync cross attention (#12449)

* graph : normalize Q, K, V shapes and add comments

ggml-ci

* context : synchronize before getting cross attention data

* model : fix command-r attention norm check
src/llama-context.cpp diff | blob | history
src/llama-graph.cpp diff | blob | history
src/llama-graph.h diff | blob | history
src/llama-model.cpp diff | blob | history
Packaging of ggml-org/llama.cpp