llama.cpp
CUDA: fix logic for clearing padding with -ngl 0
#13320

Merged

CUDA: fix logic for clearing padding with -ngl 0 #13320

JohannesGaessler merged 1 commit into ggml-org:master from JohannesGaessler:cuda-fix-deepseek-partial-offload

github-actions added Nvidia GPU

github-actions added ggml

slaren commented on 2025-05-05

JohannesGaessler force pushed 258 days ago

CUDA: fix logic for clearing padding with -ngl 0

ac78a42a

JohannesGaessler force pushed to ac78a42a 258 days ago

slaren approved these changes on 2025-05-05

JohannesGaessler merged 90703650 into master 258 days ago

Reviewers

slaren

Assignees

No one assigned

Labels

Nvidia GPU ggml

Milestone

No milestone