[Frontend] add --quick option for vllm chat/complete

[reidliu41]

• Add --quick/-q for quick API test
  • As more and more models are supported, it's useful to quickly test the API after serving.
  • -q / --quick sends a single message and prints the response.
  • Exits immediately without entering interactive mode.
  • Helpful for verifying that the model and API are working properly.

$ vllm chat --help
  -q MESSAGE, --quick MESSAGE
                        Send a single prompt as MESSAGE and print the response, then exit. (default:
                        None)

  -q PROMPT, --quick PROMPT
                        Send a single prompt and print the completion output, then exit. (default:
                        None)

$ vllm chat -q "who are you?"
Using model: qwen/Qwen1.5-0.5B-Chat
I am a large language model created by Alibaba Cloud. My name is Qwen.

[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.

🚀

[reidliu41]

hello @DarkLight1337 could you please help to take a look or assign appropriate to review?

[DarkLight1337]

LGTM now, thanks