test: relax VLM input format assertions for image understanding#12755
Merged
zhaochenyang20 merged 1 commit intosgl-project:refactor-engine-vlm-paramsfrom Nov 6, 2025
Conversation
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
23ed885
into
sgl-project:refactor-engine-vlm-params
1 check passed
minleminzui
added a commit
to minleminzui/sglang
that referenced
this pull request
Nov 16, 2025
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Make VLMInputTestBase.verify_response less brittle by checking for
keywords (taxi/car + SG/SGL/logo/company) instead of enforcing exact
phrasing like "sg" and "text". This keeps the test focused on whether
the model understands the two images while avoiding overfitting to a
specific generation style across Qwen and Gemma.
#10532
Modifications
Accuracy Tests
Benchmarking and Profiling
Checklist