[Kernel][ROCm][AMD] fp8 moe configs for MI300X. Mixtral-8x(7B,22B) TP=1,2,4,8

[divakar-amd]

fp8 moe configs for Mixtral-8x7B and 8x22B for TP=1,2,4,8

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.
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 do one of these:

• Add ready label to the PR
• Enable auto-merge.

🚀

[divakar-amd]

/ready

[divakar-amd]

@DarkLight1337 @mgoin @simon-mo

[DarkLight1337]

Sorry for forgetting about this!

[mgoin]

@divakar-amd could you please merge with current main? Your CI failures seem like previous known failures

[divakar-amd]

This PR used old triton version (num_stages=0).
Closing this PR in favor of the latest #12408