llama.cpp
CUDA: add log line when mxfp4 acceleration is used
#18483

Merged

CUDA: add log line when mxfp4 acceleration is used #18483

am17an merged 2 commits into ggml-org:master from am17an:add-log-mxfp4

am17an requested a review from

JohannesGaessler 178 days ago

am17an requested a review from

ggerganov 178 days ago

CUDA: add log line when mxfp4 acceleration is used

0832b483

am17an force pushed from 5233b61c to 0832b483 178 days ago

github-actions added Nvidia GPU

github-actions added ggml

add in backend_get_features

e9976e3d

ggerganov approved these changes on 2025-12-30

am17an merged d77d7c5c into master 178 days ago

am17an deleted the add-log-mxfp4 branch 178 days ago

Reviewers

ggerganov

JohannesGaessler

Assignees

No one assigned

Labels

Nvidia GPU ggml

Milestone

No milestone