add smollm3 support

[NouamaneTazi]

Essential Elements of an Effective PR Description Checklist

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan, such as providing test command.
• The test results, such as pasting the results comparison before and after, or e2e results
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.

Purpose

Testing matching logits for SmolLM3 using transformers backend
Testing some vllm's features (TBA..)

-> Works with huggingface/transformers#38755

(Optional) Documentation Update

[github-actions]

👋 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.

🚀

[gemini-code-assist]

Summary of Changes

Hello @NouamaneTazi, 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 full support for the SmolLM3 model, integrating its architecture and enabling its use with existing system features. The changes involve adding the model's specific components and updating registries to recognize and utilize it.

Highlights

• New Model Integration: Adds comprehensive support for the SmolLM3 model, enabling its loading and efficient execution within the system.
• Core Architecture Implementation: Introduces the specific architectural components of SmolLM3, including its Multi-Layer Perceptron (MLP), Attention mechanism, and Decoder Layer, optimized for inference.
• System Registry Updates: Integrates SmolLM3 into the model registries, making it discoverable for both testing and runtime model execution.
• Feature Compatibility: Ensures the newly added SmolLM3 model is compatible with existing vLLM features such as quantization, LoRA, and pipeline parallelism.

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

1. 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. ↩

[gemini-code-assist]

Code Review

This pull request adds support for the SmolLM3 model. The changes include registering the model in the tests and model executor registries, and a new file vllm/model_executor/models/smollm3.py containing the model implementation.

The implementation largely follows vLLM's established patterns for new models, including support for tensor parallelism, pipeline parallelism (via SupportsPP), LoRA (via SupportsLoRA), and torch.compile.

One critical issue was found in smollm3.py related to the application of Rotary Positional Embeddings (RoPE), where the condition to use RoPE seems inverted. This has been flagged with a critical severity.

Additionally, while the PR description mentions testing, it would be beneficial for maintainability if the PR description checklist was more comprehensively filled out, particularly regarding test commands. For a new model addition, updating relevant documentation like supported_models.md and potentially adding an example would also be valuable, though this is marked as optional in the template.

[mergify]

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

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

[hmellor]

Thank you for the PR. I have benchmarked this dedicated implementation against the Transformers backend and the performance gap is <5%.

Given that we plan to close this gap with further improvements to the Transformers backend and the Transformers modelling code, I'm going to close this as superseded by #22665.