[AMD][MI30X]Update Qwen3.5 perf

[cquil11]

Warning

This PR is a reopen of #986, which was reverted in #1062 due to an error with the first PR. The contents and description are otherwise identical to the original.

Note: MI355X scripts are intentionally NOT re-applied here because PR #1036 landed subsequent fixes to those files that should be preserved.

• Added new config keys for Qwen3.5 BF16 and FP8 benchmarks on MI300X and MI325X.
• Updated Docker image to lmsysorg/sglang:v0.5.10-rocm720-mi30x for better compatibility.
• Enhanced benchmark scripts with additional parameters for context length and prefill tokens.
• Adjusted memory fraction settings and added new flags for server launch to optimize performance.

e2e Test: https://github.com/SemiAnalysisAI/InferenceX/actions/runs/24170176668

Co-Authored-by: @chunfangamd @1am9trash

[github-actions]

Thanks for the contribution! For vLLM & SGLang, please ensure that your recipes is similar to the official vLLM recipes and/or the SGLang cookbook

• https://cookbook.sglang.io/
• https://docs.vllm.ai/projects/recipes/en/latest/

If it is not, please create a PR first before we can merge your PR into the master branch. Let's ensure that the documentation is first class such that the entire ML community can benefit from your hard work! Thank you

• https://github.com/vllm-project/recipes
• https://github.com/sgl-project/sgl-cookbook

PR authors are responsible for ensuring that after merging, all GitHub Action jobs fully pass. A lot of the time, failures are just flakes and simply re-running the failed jobs will fix it. If re-running failed jobs is attempted, PR authors are responsible for ensuring it passes. See GitHub's docs on re-running failed jobs: https://docs.github.com/en/actions/how-tos/manage-workflow-runs/re-run-workflows-and-jobs#re-running-failed-jobs-in-a-workflow

If additional help is needed, PR authors can reach out to core maintainers over Slack.