llama.cpp
CUDA : looped PAD kernel for more than 65535 rows or slices
#30147

Merged

CUDA : looped PAD kernel for more than 65535 rows or slices #30147

JohannesGaessler merged 1 commit into ggml-org:master from pskrunner14:cuda-pad-grid-limit

CUDA : looped PAD kernel for more than 65535 rows or slices

0653f54a

pskrunner14 requested a review from

ggerganov 23 days ago

pskrunner14 requested a review 23 days ago

JohannesGaessler approved these changes on 2026-10-08

github-actions added testing

github-actions added ggml

github-actions added CUDA

gaugarg-nv approved these changes on 2026-10-08

JohannesGaessler merged c35b6674 into master 23 days ago

pskrunner14 deleted the cuda-pad-grid-limit branch 23 days ago

Reviewers

gaugarg-nv

JohannesGaessler

ggerganov

Assignees

No one assigned

Labels

testing ggml CUDA

Milestone

No milestone