bump flashinfer to v0.2.8

[cjackal]

Essential Elements of an Effective PR Description Checklist

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan, such as providing test command.
• The test results, such as pasting the results comparison before and after, or e2e results

Purpose

Bump flashinfer version in official vllm docker image to v0.2.8, the latest stable release.

flashinfer==0.2.8 includes a QoL update for nonstandard NVSHMEM location support, which is especially useful for vllm users experimenting with expert parallelism by stacking EP libraries on top of vllm docker image.

Test Plan

docker build CI is green

Test Result

TBD

[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.

🚀

[gemini-code-assist]

Code Review

This pull request updates the flashinfer dependency version from a release candidate (v0.2.8rc1) to the final stable release (v0.2.8) within the Dockerfile. The change is minimal, correct, and aligns with the stated purpose of using the latest stable version of the library. I see no issues with this update.

[mgoin]

Thank you for the bump!

[cjackal]

CI failures in basic model tests are fixed in #21375.

[cjackal]

@mgoin It seems TPU test has timed out and all other tests pass.