[CI Fix] Pin tests/models/registry.py MiniMaxText01ForCausalLM to revision due to model changes #20199
Conversation
Signed-off-by: mgoin <mgoin64@gmail.com>
|
👋 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 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 🚀 |
There was a problem hiding this comment.
Summary of Changes
Hello @mgoin, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
This pull request provides a temporary fix for a continuous integration (CI) failure. It addresses an issue where an upstream change to the MiniMax-Text-01 model definition caused our existing tests to break. The immediate solution is to mark this specific model as unavailable online within our test registry, thereby skipping its associated tests and unblocking CI, with a follow-up planned to properly integrate the updated model definition.
Highlights
- CI Fix: Implemented a temporary measure to resolve continuous integration (CI) failures caused by an upstream change in the
MiniMax-Text-01model definition. - Test Configuration: Configured the
MiniMaxText01ForCausalLMmodel withintests/models/registry.pyto be temporarily marked asis_available_online=False, which causes its online availability tests to be skipped.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| Feature | Command | Description |
|---|---|---|
| Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
| Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
| Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
| Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
Signed-off-by: mgoin <mgoin64@gmail.com>
|
Does this mean that this model is currently broken if users launch it with default args? |
|
@ywang96, good point. I may create an issue to track the breakage of the latest min-max model? |
|
I think I have a patch to support the new format, will post in a few hours |
…ision due to model changes (vllm-project#20199) Signed-off-by: mgoin <mgoin64@gmail.com>
…ision due to model changes (vllm-project#20199) Signed-off-by: mgoin <mgoin64@gmail.com> Signed-off-by: avigny <47987522+avigny@users.noreply.github.com>
…ision due to model changes (vllm-project#20199) Signed-off-by: mgoin <mgoin64@gmail.com>
Purpose
FIX #20198
It seems like the model definition has changed upstream this morning https://huggingface.co/MiniMaxAI/MiniMax-Text-01/commit/130e821701f3244ab18bab619dbd6fa9b5a92d28
This caused our implementation to start failing and falling back to the Transformers implementation, which doesn't work yet.
We will need to update the definition in vLLM to support the new "HF format" of
MiniMaxForCausalLM, but we should do that in another PR. This one is just to pin to the older format in the meantime.Test Plan
pytest -s -v "tests/models/test_initialization.py::test_can_initialize[MiniMaxText01ForCausalLM]"Test Result
Local pass