Make sure the correct version of ao is installed in CI

[drisspg]

Essential Elements of an Effective PR Description Checklist

Purpose

Fix hardcoded CUDA version in torchao installation to use dynamic CUDA version detection

Test Plan

Run the quantization test pipeline with different CUDA versions to ensure torchao is installed from the correct index URL:

# The pipeline will now use the appropriate CUDA version
CUDA_VERSION=12.8 .buildkite/test-pipeline.yaml

Test Result

The torchao package will be installed from the correct PyTorch wheel index based on the system's CUDA version (e.g., cu128 for CUDA 12.8, cu121 for CUDA 12.1) instead of always using cu126.

[github-actions[bot]]

👋 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.

🚀

[drisspg]

cc @huydhn, @houseroad

[DarkLight1337]

Can you merge from main to see if the CI failures can be resolved?

[mergify[bot]]

This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @drisspg.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork