[V1] Update structured output offline inference example

[russellb]

Update this example to work with V1. The grammar specified was not
comaptible with xgrammar. This worked with V0 as we would automatically
fall back to outlines.

In V1 we have fallback support, but you have to opt-in to it by setting
your backend to auto. Grammar type support varies among the backends.

Signed-off-by: Russell Bryant rbryant@redhat.com

[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.

🚀

[russellb]

This change would make the current example work: #15724

but this seems worth landing now to make sure we have something that works, including for recent releases that use V1

[hmellor]

LGTM.

Could you add r to the start of the regex to remove the warning SyntaxWarning: invalid escape sequence '\w' guided_decoding_params = GuidedDecodingParams(regex="\w+@\w+\.com\n")?

[russellb]

LGTM.

Could you add r to the start of the regex to remove the warning SyntaxWarning: invalid escape sequence '\w' guided_decoding_params = GuidedDecodingParams(regex="\w+@\w+\.com\n")?

done!