Skip to content

Move pytorch transforms from init method to transform method - #1303

Draft
quic-mamta wants to merge 6 commits into
quic:mainfrom
quic-mamta:move_pt_transforms
Draft

quic-mamta wants to merge 6 commits into
quic:mainfrom
quic-mamta:move_pt_transforms

Conversation

@quic-mamta

Copy link
Copy Markdown
Contributor
  • Moving all pytorch transforms from init method to transform method in in base model classQ EFFBaseModel instead of Auto classes in modeling_auto.py.
  • This will help to scale blocking strategies and simplify qaic_config usage.

@quic-mamta quic-mamta self-assigned this Sep 2, 2026
@quic-mamta
quic-mamta marked this pull request as draft September 2, 2026 09:55
@quic-mamta
quic-mamta force-pushed the move_pt_transforms branch 5 times, most recently from e471c19 to ed95a95 Compare September 7, 2026 14:08
Signed-off-by: Mamta Singh <mamtsing@qti.qualcomm.com>
Signed-off-by: Mamta Singh <mamtsing@qti.qualcomm.com>
…user facing API

Signed-off-by: Mamta Singh <mamtsing@qti.qualcomm.com>
quic-mamta and others added 2 commits September 22, 2026 14:34
Signed-off-by: Mamta Singh <168400541+quic-mamta@users.noreply.github.com>
Signed-off-by: Mamta Singh <mamtsing@qti.qualcomm.com>
Signed-off-by: Mamta Singh <mamtsing@qti.qualcomm.com>

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant