Serverless GPU lab with APIM and SGLang

[nourshaker-msft]

Purpose

Showcase the capabilities of serverless GPU to host custom models that can scale down to Zero to run models that would otherwise not have access to in certain regions.

Does this introduce a breaking change?

[ ] Yes
[x] No

Pull Request Type

What kind of change does this Pull Request introduce?

[ ] Bugfix
[x] Feature
[ ] Code style update (formatting, local variables)
[ ] Refactoring (no functional changes, no api changes)
[ ] Documentation content changes
[ ] Other... Please describe:

How to Test

• Get the code

• Run the serverless-gpu lab

• CLEAN UP to avoid excessive costs

Other Information

[github-actions]

📋 Labs Config Preview

The following labs will be updated in docs/labs-config.json when this PR is merged:

• serverless-gpu

The config will be updated on both main and gh-pages branches.

[github-actions]

📋 Labs Config Preview

The following labs will be updated in docs/labs-config.json when this PR is merged:

• serverless-gpu

The config will be updated on both main and gh-pages branches.

[github-actions]

📋 Labs Config Preview

The following labs will be updated in docs/labs-config.json when this PR is merged:

• serverless-gpu

The config will be updated on both main and gh-pages branches.