]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: bfdf581)
CUDA: extend K-type validation to V-types for flash attention (#24403)
authorAlexey Kopytko <redacted>
Mon, 6 Jul 2026 14:26:50 +0000 (23:26 +0900)
committerGitHub <redacted>
Mon, 6 Jul 2026 14:26:50 +0000 (16:26 +0200)
commitcb295bf59663cd3577389315636772f4060bd1f5
tree667f883d573ff5d25a2d5db50d3440bb7ebad35etree
parentbfdf581b8b2a3c8e999227a44dfa3e890f1038bdcommit | diff
CUDA: extend K-type validation to V-types for flash attention (#24403)

* CUDA: extend K-type validation to V-types for flash attention

* reorder
ggml/src/ggml-cuda/fattn.cu diff | blob | history
Packaging of ggml-org/llama.cpp