[AMD] Pull latest SGLang version for AMD CI

[quitenode]

Motivation

Enhance amd_ci_start_container.sh to dynamically retrieve SGLang version from version.py, with a fallback option. Update default base tags for MI30X and MI35X to use the retrieved version.

Continue of #8070

Modifications

Accuracy Test

Benchmark & Profiling

Checklist

• Format your code according to the Code Formatting with Pre-Commit.
• Add unit tests as outlined in the Running Unit Tests.
• Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
• Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
• For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.
• Please feel free to join our Slack channel at https://slack.sglang.ai to discuss your PR.

[gemini-code-assist]

Summary of Changes

Hello @michael-amd, 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!

I've updated the amd_ci_start_container.sh script to dynamically retrieve the SGLang version from version.py. This change ensures that the CI process for AMD platforms (MI30X and MI35X) always uses the correct and up-to-date SGLang version for its base tags, improving consistency and reducing manual updates.

Highlights

• Dynamic Version Retrieval: The amd_ci_start_container.sh script now includes logic to read the SGLang version directly from python/sglang/version.py.
• Version Extraction Logic: A Python one-liner is used within the shell script to parse version.py and extract the __version__ string using regular expressions.
• Fallback Mechanism: A fallback version (v0.4.10.post2) is provided in case version.py is not found or the version cannot be extracted, ensuring the script remains functional.
• Updated Base Tags: The DEFAULT_MI30X_BASE_TAG and DEFAULT_MI35X_BASE_TAG variables are now constructed using the dynamically retrieved SGLang version, replacing hardcoded values.

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 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 or fill out our survey 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 enhances the AMD CI script to dynamically retrieve the SGLang version, which is a good improvement over hardcoded values. My review focuses on making the version retrieval logic more robust and maintainable by addressing potential issues like duplicated code and silent fallbacks. The suggested changes will improve the script's reliability.

[quitenode]

https://github.com/sgl-project/sglang/actions/runs/16742434839/job/47393424059?pr=8787

Run bash scripts/amd_ci_start_container.sh
Using SGLang version: v0.4.10.post2
Extracted runner from hostname: linux-mi325-gpu-1
The runner is: linux-mi325-gpu-1
Runner is linux-mi325-gpu-1, will find mi30x image.
Checking for image: rocm/sgl-dev:v0.4.10.post2-rocm630-mi30x-20250805
Found available image: rocm/sgl-dev:v0.4.10.post2-rocm630-mi30x-20250805
Pulling Docker image: rocm/sgl-dev:v0.4.10.post2-rocm630-mi30x-20250805
v0.4.10.post2-rocm630-mi30x-20250805: Pulling from rocm/sgl-dev

[quitenode]

Hi @saienduri, could I ask how to know current rocm version for mi30x and mi35x so I will remove the hard code rocm version?

[saienduri]

Okay to use hardcoded rocm version

[quitenode]

@saienduri could you help to approve? cc: @HaiShaw

Okay to use hardcoded rocm version

[gemini-code-assist]

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!