Skip to content

Conversation

@gcanlin
Copy link
Contributor

@gcanlin gcanlin commented Nov 3, 2025

What this PR does / why we need it?

Closes #3508.

To continuously monitor the accuracy of the Qwen3-VL-8B-Instruct model, this PR adds the corresponding configuration file to the CI.
The current accuracy is around 0.55, and gpu_memory_utilization is set to 0.5 to prevent OOM issues.

Does this PR introduce any user-facing change?

How was this patch tested?

pytest -sv ./tests/e2e/models/test_lm_eval_correctness.py --config ./tests/e2e/models/configs/Qwen3-VL-8B-Instruct.yaml

Signed-off-by: gcanlin <canlinguosdu@gmail.com>
@github-actions
Copy link

github-actions bot commented Nov 3, 2025

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

  • A PR should do only one thing, smaller PRs enable faster reviews.
  • Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
  • Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request adds a new accuracy evaluation configuration for the Qwen3-VL-8B-Instruct model. The changes are straightforward, involving the creation of a new YAML configuration file and updating the list of test configurations. My review includes one suggestion to improve file formatting by adding a newline character at the end of accuracy.txt. This change will ensure compliance with POSIX standards and prevent potential issues with various development tools.

@github-actions
Copy link

github-actions bot commented Nov 4, 2025

This pull request has conflicts, please resolve those before we can evaluate the pull request.

@gcanlin
Copy link
Contributor Author

gcanlin commented Nov 4, 2025

Close this PR because it duplicates #3823.

@gcanlin gcanlin closed this Nov 4, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[RFC]: Multi-Modal Tasks

1 participant