transformers
Fix CUDA Graph breaking host to device copy from scalar tensor allocation
#47547
Merged
Overview
Commits
4
Changes
View On GitHub

Fix CUDA Graph breaking host to device copy from scalar tensor allocation #47547

hmellor merged 4 commits into main from gemma-4-cuda-graphs
hmellor
hmellor Make Gemma 4 CUDA Graph compilable
b30cd15e
HuggingFaceDocBuilderDev
vasqu
vasqu approved these changes on 2026-07-28
hmellor
vasqu
hmellor fix everywhere
2e0e48be
vasqu
hmellor hmellor changed the title Make Gemma 4 CUDA Graph compilable Fix CUDA Graph breaking host to device copy from scalar tensor allocation 82 days ago
hmellor
github-actions
hmellor Merge branch 'main' into gemma-4-cuda-graphs
1c79f1b0
hmellor hmellor enabled auto-merge 81 days ago
hmellor Run modular conversion for instructblipvideo
4db4a37b
github-actions
hmellor hmellor merged 0f93ffab into main 81 days ago
hmellor hmellor deleted the gemma-4-cuda-graphs branch 81 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum