Fix QwenImage txt_seq_lens handling #12702
Open
+210
−130
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
|
just a few comments, not a full review:
|
dxqb
reviewed
Nov 29, 2025
| raise ValueError(f"`txt_seq_lens` must have length {batch_size}, but got {len(txt_seq_lens)} instead.") | ||
| text_seq_len = max(text_seq_len, max(txt_seq_lens)) | ||
| elif encoder_hidden_states_mask is not None: | ||
| text_seq_len = max(text_seq_len, int(encoder_hidden_states_mask.sum(dim=1).max().item())) |
There was a problem hiding this comment.
This only works if the attention mask is in the form of [True, True, True, ..., False, False, False]. While this is the case in the most common use case of text attention masks, it doesn't have to be the case.
If the mask is [True, False, True, False, True, False], self.pos_embed receives an incorrect sequence length
Contributor
Author
|
thanks @dxqb the idea was to remove |
- Remove seq_lens parameter from dispatch_attention_fn - Update varlen backends to extract seqlens from masks - Update QwenImage to pass 2D joint_attention_mask - Fix native backend to handle 2D boolean masks - Fix sage_varlen seqlens_q to match seqlens_k for self-attention Note: sage_varlen still producing black images, needs further investigation
…to txt_seq_lens
Member
6 tasks
Contributor
Author
|
some benchmarks with various backends: code: 
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
txt_seq_lensplumbing from all QwenImage pipelines and modular steps; the transformer now infers text length from encoder inputs/masks and validates optional overrides.encoder_hidden_states_maskinside the double-stream attention, avoiding fullseq_len²masks while keeping padding tokens masked.txt_seq_lensvalues and encoder masks are handled safely.Fixes #12344
Before submitting
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.