[GB300][vLLM] Add MiniMax-M2.5 FP4 disagg Dynamo configs

[Ankur-singh]

GB300 half of split #1560 (B300 sibling lives in a separate PR so one CI failure doesn't block the other).

Summary

• Add minimaxm2.5-fp4-gb300-dynamo-vllm to .github/configs/nvidia-master.yaml (1k1k + 8k1k search spaces)
• Add srt-slurm vLLM recipes under benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m2.5/
• Wire minimaxm2.5 + fp4 + dynamo-vllm routing into runners/launch_gb300-nv.sh and runners/launch_gb300-cw.sh
• Append perf-changelog entry

Image: vllm/vllm-openai:v0.20.1; model: nvidia/MiniMax-M2.5-NVFP4.

---

Note

Low Risk
Benchmark and runner wiring only; no production app or auth changes. Misconfigured paths could fail CI sweeps on GB300 clusters.

Overview
Adds GB300 coverage for MiniMax-M2.5 NVFP4 disaggregated Dynamo + vLLM multinode benchmarks, parallel to the existing GB200 entry.

Registers minimaxm2.5-fp4-gb300-dynamo-vllm in nvidia-master.yaml with 1k1k and 8k1k fixed-seq-len search spaces (varying prefill/decode workers, TP/EP, and CONFIG_FILE recipe paths). Introduces a new recipe tree under benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m2.5/ (tp4, tp4ep, dep2/dep8, 8k variants) wired to vllm/vllm-openai:v0.20.1, Dynamo 1.2.0 dev wheel, and Nixl KV transfer.

Launch scripts on GB300 (launch_gb300-nv.sh, launch_gb300-cw.sh) now route minimaxm2.5 + fp4 + dynamo-vllm: model paths on scratch/vast, srt-slurm clone on main, recipe copy into recipes/vllm/minimax-m2.5, and minimax-m2.5-nvfp4 in srtslurm.yaml model_paths. perf-changelog documents the new config key.

^{Reviewed by Cursor Bugbot for commit dcc0f2b. Bugbot is set up for automated code reviews on this repo. Configure here.}

[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://docs.sglang.io/cookbook/intro
• https://recipes.vllm.ai/

If it is not, please create a PR first before we can merge your single node 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/sglang/tree/main/docs_new

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

As a rule of thumb, generally, PR authors should request a review & get a PR approval from the respective companies' CODEOWNERS before requesting a review from core maintainers.

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

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26856828826
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26856828826

[jasonlizhengjian]

@Ankur-singh I also have this in progress on #1641

[Ankur-singh]

@jasonlizhengjian Noted. Closing this one!