[Model] Add support for MiniMaxM1ForCausalLM (shares architecture with MiniMaxText01ForCausalLM) #19677
Conversation
There was a problem hiding this comment.
Summary of Changes
Hello @qscqesze, 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 introduces support for the MiniMaxM1ForCausalLM model. Since it shares the same underlying architecture as MiniMaxText01ForCausalLM, the implementation leverages an alias in the model registry, avoiding redundant code and simplifying maintenance. The changes include updates to the model registry, documentation, and test configurations.
Highlights
- New Model Support: Added official support for the
MiniMaxM1ForCausalLMmodel. - Architecture Alias: Implemented support by aliasing
MiniMaxM1ForCausalLMto the existingMiniMaxText01ForCausalLMimplementation, as they share the same architecture. - Documentation and Testing: Updated the supported models documentation and added an example model ID for testing.
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 configureGemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
|
👋 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.
Code Review
This PR adds support for MiniMaxM1ForCausalLM by aliasing it to MiniMaxText01ForCausalLM. The changes update model registries and documentation. Verify that the Hugging Face configuration for the new model is fully compatible with the existing vLLM model code to prevent runtime issues.
Head branch was pushed to by a user without write access
|
@ywang96 I noticed that the CI check has failed, but as far as I can tell, our changes are limited to documentation updates and configuration adjustments for model usage, which should not affect the final results. |
|
Retrying the test |
|
For anyone want to use this model, you can use vLLM nightly wheels to test it out!
|
|
is there any extra param to disable reasoning ? something similar to enable_thinking false from Qwen 3 ? |
…h MiniMaxText01ForCausalLM) (vllm-project#19677) Signed-off-by: QscQ <qscqesze@gmail.com>
…h MiniMaxText01ForCausalLM) (vllm-project#19677) Signed-off-by: QscQ <qscqesze@gmail.com> Signed-off-by: minpeter <kali2005611@gmail.com>
…h MiniMaxText01ForCausalLM) (vllm-project#19677) Signed-off-by: QscQ <qscqesze@gmail.com> Signed-off-by: Yang Wang <elainewy@meta.com>
…h MiniMaxText01ForCausalLM) (vllm-project#19677) Signed-off-by: QscQ <qscqesze@gmail.com>
…h MiniMaxText01ForCausalLM) (vllm-project#19677) Signed-off-by: QscQ <qscqesze@gmail.com>
…h MiniMaxText01ForCausalLM) (vllm-project#19677) Signed-off-by: QscQ <qscqesze@gmail.com> Signed-off-by: avigny <47987522+avigny@users.noreply.github.com>
…h MiniMaxText01ForCausalLM) (vllm-project#19677) Signed-off-by: QscQ <qscqesze@gmail.com>
We would like to propose official support for the MiniMaxM1ForCausalLM model within vLLM. This model shares the exact same architecture and inference behavior as MiniMaxText01ForCausalLM, and is essentially a variant with different weights.
To support this, we added an alias in the vLLM codebase that maps MiniMaxM1ForCausalLM to the existing MiniMaxText01ForCausalLM implementation. This allows the new model to be used seamlessly without requiring redundant code or changes to the inference pipeline.