vllm icon indicating copy to clipboard operation
vllm copied to clipboard

[ci] Consolidate Qwen models

Open khluu opened this issue 10 months ago • 6 comments

Try to convert as many Qwen and Qwen2 to Qwen2.5 and reduce model size as we can.

khluu avatar Feb 11 '25 22:02 khluu

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

github-actions[bot] avatar Feb 11 '25 22:02 github-actions[bot]

Qwen shares the same architecture with Qwen-VL so I'd like to keep at least one test to check that the text-only version works correctly (there have been regressions in the past due to updating Qwen-VL)

DarkLight1337 avatar Feb 12 '25 04:02 DarkLight1337

Qwen shares the same architecture with Qwen-VL so I'd like to keep at least one test to check that the text-only version works correctly (there have been regressions in the past due to updating Qwen-VL)

okay I just reverted test_chat_echo to use Qwen2 still

khluu avatar Feb 12 '25 06:02 khluu

Qwen shares the same architecture with Qwen-VL so I'd like to keep at least one test to check that the text-only version works correctly (there have been regressions in the past due to updating Qwen-VL)

okay I just reverted test_chat_echo to use Qwen2 still

We need to load the Qwen (V1) model specifically, at least untilr #13157 is merged - afterwards we should be free to remove the test outright.

DarkLight1337 avatar Feb 12 '25 17:02 DarkLight1337

This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @khluu.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

mergify[bot] avatar Feb 13 '25 22:02 mergify[bot]

This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @khluu.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

mergify[bot] avatar Feb 18 '25 11:02 mergify[bot]

I guess this isn't necessary anymore?

DarkLight1337 avatar Feb 22 '25 13:02 DarkLight1337

yep let me close the PR

I guess this isn't necessary anymore?

khluu avatar Feb 22 '25 13:02 khluu