[DRAFT] [AMD] Update Minimax M2.5 MI325 image and adjust search space

[benenzhu]

• config-keys:

  • minimaxm2.5-fp8-mi325x-vllm
    description:
  • "Upgrade vLLM ROCm image from v0.16.0 to v0.18.0"
  • "Replace TP4 with TP8/EP8, add conc range 4-256"
    pr-link: [DRAFT] [AMD] Update Minimax M2.5 MI325 image and adjust search space #953

  Tmp not change MI300x configs cause running with some error.

[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

[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

[functionstackx]

@chunfangamd is @benenzhu part of AMD? can u confirm internally? if so, plz add him to the upstream repo. better developer experience to create branches in upstream then do forks. for example, forks, we can do sweep-enabled label to validate PRs

[benenzhu]

@chunfangamd is @benenzhu part of AMD? can u confirm internally? if so, plz add him to the upstream repo. better developer experience to create branches in upstream then do forks. for example, forks, we can do sweep-enabled label to validate PRs

Hi I am from AMD and already in the repo with the help of @chunfangamd. Though this branch name is starting with amd/ maybe a little confusing .

[chunfangamd]

LGTM