[AMD] Add MiniMax-M3-FP8 MI355X ATOM non-EAGLE3 & EAGLE3

[seungrokj]

Summary

• Add minimaxm3-fp8-mi355x-atom CI recipe: single-node ATOM benchmark for MiniMax-M3-MXFP8 on MI355X
• Add minimaxm3-fp8-mi355x-atom-mtp CI recipe: same with EAGLE3 speculative decoding (3 draft tokens)
• Both use rocm/atom-dev:MiniMax-M3-20260619 image, search space mirrors the FP4 atom variants (ISL=1024,8192 OSL=1024 TP2/TP4/TP8)

Test plan

• Server launches correctly for FP8 checkpoint
• EAGLE3 spec args pass through correctly for mtp variant
• CI sweep triggers on mi355x runner for both configs

🤖 Generated with Claude Code

---

Note

Low Risk
Benchmark and CI configuration only; no changes to production serving, auth, or core inference logic.

Overview
Adds MiniMax-M3 MXFP8 single-node ATOM coverage on MI355X for CI throughput sweeps.

Two new entries in amd-master.yaml — minimaxm3-fp8-mi355x-atom and minimaxm3-fp8-mi355x-atom-mtp — both use rocm/atom-dev:MiniMax-M3-20260619, MiniMaxAI/MiniMax-M3-MXFP8, fixed-seq-len ISL 1024/8192 with OSL 1024, and TP4 concurrency sweeps (conc 1–256). The MTP config marks spec-decoding: mtp on the same search space.

New shell runners start atom.entrypoints.openai_server with block size 128 and 0.8 GPU memory utilization; the MTP script adds EAGLE3 args (Inferact/MiniMax-M3-EAGLE3, 3 speculative tokens) and enables --use-chat-template on the serving benchmark. FP8 KV cache remains commented out as not yet supported.

perf-changelog.yaml documents both config keys for PR #1867.

^{Reviewed by Cursor Bugbot for commit 3913e9a. 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.

---

感谢你的贡献！对于 vLLM 与 SGLang，请确保你的 recipe 与官方 vLLM recipes 和/或 SGLang cookbook 保持一致

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

如果不一致，请先创建一个 PR，之后我们才能将你的单节点 PR 合并到 master 分支。让我们确保文档保持一流水准，使整个 ML 社区都能从你的辛勤工作中受益！谢谢

• https://github.com/vllm-project/recipes
• https://github.com/sgl-project/sglang/tree/main/docs_new

PR 作者有责任确保合并后所有 GitHub Action 任务完全通过。 很多时候失败只是偶发抖动（flake），重新运行失败的任务即可解决。如果选择重新运行失败的任务，PR 作者有责任确保其最终通过。参见 GitHub 关于重新运行失败任务的文档：https://docs.github.com/en/actions/how-tos/manage-workflow-runs/re-run-workflows-and-jobs#re-running-failed-jobs-in-a-workflow

一般而言，PR 作者应先向相应公司的 CODEOWNERS 请求审阅并获得 PR 批准，然后再请求核心维护者审阅。

如需更多帮助，PR 作者可通过 Slack 联系核心维护者。

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=27860917145
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=27860917145

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=27862137852
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=27862137852

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit 196961a. Configure here.}

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=27862752989
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=27862752989

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=27862873087
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=27862873087

[seungrokj]

/reuse-sweep-run

[seungrokj]

/merge-prs

[functionstackx]

/merge-prs

/merge-prs isnt an github comment fyi, it is an claude code command u type into claude code CLI https://code.claude.com/docs/en/commands @seungrokj