[BugFix] Fix Qwen3 Omni talker mtp torch.compile startup error#1104
Merged
hsliuustc0106 merged 6 commits intovllm-project:mainfrom Jan 30, 2026
Merged
Conversation
…predictor The original code used a pre-computed position_ids_buffer with batch_size-dependent slicing, which caused torch.compile to specialize batch_size as a constant. This conflicted with vLLM's @support_torch_compile decorator that marks batch_size as dynamic, resulting in ConstraintViolationError. Changed to dynamically compute position_ids using torch.arange().repeat() to avoid the specialization issue while maintaining correct behavior. Signed-off-by: ram16g <[email protected]>
Signed-off-by: ZeldaHuang <[email protected]>
1 task
5 tasks
Signed-off-by: ZeldaHuang <[email protected]>
Signed-off-by: ZeldaHuang <[email protected]>
5 tasks
5 tasks
dongbo910220
pushed a commit
to dongbo910220/vllm-omni
that referenced
this pull request
Feb 1, 2026
…project#1104) Signed-off-by: ram16g <[email protected]> Signed-off-by: ZeldaHuang <[email protected]> Co-authored-by: ram16g <[email protected]> Co-authored-by: Hongsheng Liu <[email protected]>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED.
Purpose
ref #1048 and #1102
Talker mtp occurred startup error when use torch compile with small max_batch_size(1 and 2)
Test Plan
Test Result
Confirmed with small max_batch_size(1、2、3)
Essential Elements of an Effective PR Description Checklist
supported_models.mdandexamplesfor a new model.BEFORE SUBMITTING, PLEASE READ https://github.com/vllm-project/vllm-omni/blob/main/CONTRIBUTING.md (anything written below this line will be removed by GitHub Actions)