Add workflow to build vLLM-TPU wheel using PyPI tpu-inference

[ylangtsou]

Description

A new workflow to build and test vllm-tpu using the nightly tpu-inference package from PyPI, instead of building it from source and verify that the wheel builds and installs successfully, with vllm serve starting up correctly in an E2E environment. A 20-minute delay will be incorporated to allow sufficient time for the tpu-inference package to be published.

Tests

Pass on buildkite
Failed due to timeout on Buildkite

Checklist

Before submitting this PR, please make sure:

• I have performed a self-review of my code.
• I have necessary comments in my code, particularly in hard-to-understand areas.

[dennisYehCienet]

I think it's pretty good. Just a few things I want to mention.

It seems like you haven't included the main.yml procedure in your test.
Both steps depend on the record_verified_commit_hashes step, but your current Buildkite tests do not include it.
Please use main.yml to run a few test cases similar to our normal Buildkite procedure.

And, please provide two types of tests:
one that successfully pulls from PyPI and runs, and the other that fails after 20 minutes (due to timeout).
Please put these two test links into the PR description. You can then remove some of the testing code in the PR to make it formal.

Please update the PR description as well, as some information might be outdated. And we don't need to mention every file's changes, a brief summary of the PR is sufficient.

[QiliangCui]

can do the "add argument and enable v7" as well? not to be in the same PR but after merging and verify this.

[QiliangCui]

a TODO:

instead of putting the "if nightly==1" inside the pipeline.yml. can we do the if check here and load "nightly" pipeline only when nightly==1?

• @weiyu0824 for awareness, too.