transformers
[Qwen3Next] preserve linear-attn-mask optimization under torch.compile/export
#46148
Open
Overview
Commits
2
Changes
View On GitHub

[Qwen3Next] preserve linear-attn-mask optimization under torch.compile/export #46148

yuvrajsharma9981 wants to merge 2 commits into huggingface:main from yuvrajsharma9981:yuvi/qwen3_5-export-compat
yuvrajsharma9981
yuvrajsharma9981 [Qwen3.5] preserve linear-attn-mask optimization under torch.compile/…
65471818
yuvrajsharma9981 Apply fix at modular source + regenerate affected modeling files
3a4e4fab
yuvrajsharma9981 yuvrajsharma9981 changed the title [Qwen3.5] preserve linear-attn-mask optimization under torch.compile/export [Qwen3Next] preserve linear-attn-mask optimization under torch.compile/export 28 days ago
github-actions
Rocketknight1

Login to write a write a comment.

Login via GitHub

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