-
Notifications
You must be signed in to change notification settings - Fork 651
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull request overview
This PR fixes the DLLM (Disaggregated Large Language Model) mask handling in the set_step method. The change modifies how mask values are updated when the sequence step boundary is reset.
Changes:
- Modified the
set_stepmethod inSchedulerSequenceDLLMto change onlyDLLM_CACHEDvalues toDLLM_UNMASKEDinstead of setting all values in the range toDLLM_MASKED
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Copilot
AI
Jan 20, 2026
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The slice should use start:end instead of start:. The variable end is calculated on line 201 but is not used in the new code. This causes the mask update to incorrectly affect elements beyond num_history_ids, potentially modifying mask values that should remain unchanged.
@RunningLeon
RunningLeon
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily receiving feedbacks. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.
Motivation
Please describe the motivation of this PR and the goal you want to achieve through this PR.
Modification
Please briefly describe what modification is made in this PR.
BC-breaking (Optional)
Does the modification introduce changes that break the backward-compatibility of the downstream repositories?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.
Use cases (Optional)
If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.
Checklist