Skip to content

CUDA backend: delete each output handle once when a program returns one tensor twice - #24420

Merged
shoumikhin merged 1 commit into
pytorch:mainfrom
shoumikhin:cuda-repeated-outputs
Nov 2, 2026
Merged

shoumikhin merged 1 commit into
pytorch:mainfrom
shoumikhin:cuda-repeated-outputs

Delete each CUDA output handle once when AOTI repeats it

dc628cc
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

1 warning and 1 notice
link-check / lint-xrefs
succeeded Nov 2, 2026 in 30s