Reland: compute M-RoPE positions for preprocessed VL inputs#21244
Merged
Reland: compute M-RoPE positions for preprocessed VL inputs#21244
Conversation
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
Collaborator
Author
|
/tag-and-rerun-ci |
Collaborator
Author
|
/rerun-failed-ci |
Fridge003
approved these changes
Mar 24, 2026
satyamk7054
pushed a commit
to satyamk7054/sglang
that referenced
this pull request
Apr 3, 2026
JustinTong0323
pushed a commit
to JustinTong0323/sglang
that referenced
this pull request
Apr 7, 2026
yhyang201
pushed a commit
to yhyang201/sglang
that referenced
this pull request
Apr 22, 2026
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
test_qwen35_models.py) was caused by an unrelated PR ([NVIDIA] Integrate FlashInfer decode kernel (Blackwell) for Qwen3.5 #19150) that added a broken FlashInfer variant for the FP4 test — that has since been disabled in Fix test_qwen35_models #21081nvidia/Qwen3.5-397B-A17B-NVFP4) since it's text-only (Qwen3_5MoeForCausalLM), not multimodalOriginal PR description (#19973)
Computes M-RoPE positions in the scheduler for multimodal requests arriving via the gRPC preprocessed path, which bypasses the normal multimodal processor. Adds
compute_mrope_positionsoverrides to QwenVL, GLM4V, and ERNIE4.5-VL processors.Test plan
test_qwen35_models.pyFlashInfer variant has been disabled