]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: a864fb1)
CUDA: add log line when mxfp4 acceleration is used (#18483)
authorAman Gupta <redacted>
Tue, 30 Dec 2025 09:40:46 +0000 (17:40 +0800)
committerGitHub <redacted>
Tue, 30 Dec 2025 09:40:46 +0000 (17:40 +0800)
commitd77d7c5c0654dc52b51f03941b12ae85d7227608
tree3578794a05b0b21853a939a5a5a02143c7c03dd1tree
parenta864fb1c14cf187831a1806c3b57e47c730afc1dcommit | diff
CUDA: add log line when mxfp4 acceleration is used (#18483)

* CUDA: add log line when mxfp4 acceleration is used

* add in backend_get_features
ggml/src/ggml-cuda/ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp