PR #19538 CUDA: loop over ne2*ne3 in case it overflows

CUDA: loop over ne2*ne3 in case it overflows #19538

am17an merged 2 commits into ggml-org:master from am17an:convert-cublas-fix

CUDA: loop over ne2*ne3 in case it overflows

3b93d390

github-actions added Nvidia GPU

github-actions added ggml

JohannesGaessler commented on 2026-02-12

use fastdiv

0fd79e57

am17an marked this pull request as ready for review 125 days ago

JohannesGaessler approved these changes on 2026-02-12

am17an merged 5065da55 into master 124 days ago

am17an deleted the convert-cublas-fix branch 124 days ago

Reviewers

JohannesGaessler

Assignees

No one assigned

Labels

Nvidia GPU ggml

Milestone

No milestone