[AMD] [DNM, still merge in 0.18 as trust_remote_code=True is not passed to quark] Add MiniMax M2.5 MXFP4 benchmark for MI355x vLLM v0.17.1 (TP=2,4)

[functionstackx]

Add MiniMax M2.5 MXFP4 benchmark config for MI355x with vLLM v0.17.1, now that AMD's MXFP4 checkpoint is out: https://huggingface.co/amd/MiniMax-M2.5-MXFP4

• Model: amd/MiniMax-M2.5-MXFP4
• Image: vllm/vllm-openai-rocm:v0.17.1
• TP=2 and TP=4 (matching MiniMax M2.5 FP8 pattern)
• VLLM_ROCM_USE_AITER=1, with AITER MoE fallback for TP>=4
• Seq lengths: 1k1k, 1k8k, 8k1k (conc 4-64)

Closes #826

Generated with Claude Code

[functionstackx]

@claude can u comment out TP=4 and only do TP=2 for now since TP=4 is bugged vllm-project/vllm#35637

[Klaud-Cold]

Claude finished @functionstackx's task in 53s —— View job

---

Commented out TP=4 for MiniMax M2.1 MXFP4

Due to vllm-project/vllm#35637, TP=4 has been disabled. Only TP=2 will run.

• Read current benchmark files
• Comment out TP=4 in .github/configs/amd-master.yaml (all 3 seq-len configs)
• Update perf-changelog.yaml with PR link and description
• Commit and push changes

Changes made:

• .github/configs/amd-master.yaml: Commented out all 3 tp: 4 search-space entries under minimaxm2.1-fp4-mi355x-vllm with a reference to the vLLM issue
• perf-changelog.yaml: Updated entry to reflect TP=2 only and added PR [AMD] [DNM, still merge in 0.18 as trust_remote_code=True is not passed to quark] Add MiniMax M2.5 MXFP4 benchmark for MI355x vLLM v0.17.1 (TP=2,4) #827 link
  |

[functionstackx]

@chunfangamd i am seeing good mxfp4 performance when comparing to FP8. just waiting for AMD to release mxfp4 version of MiniMax M2.5 now. currently AMD only have mxfp4 version of MiniMax M2.1.

[chunfangamd]

Looks good to me

[functionstackx]

@adibarra do u wanna take over this PR too? upgraading this PR to v0.18.1, this might work

[adibarra]

Sure, I'll give it a shot

[benenzhu]

@adibarra Hi, I think we need wait for vllm v0.19.1 for this. The fix PR can be found in vllm 0.19.1rc0. 0.19.0 still don't have the fix.

[adibarra]

Sounds good, we'll wait till then!

[benenzhu]

@adibarra Run passed. Wait for VLLM v0.19.1's release.

[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