[AMD] [WIP] [AGENTX] MiniMax-M3 Support on MI355X with MTP

[ajith-sirra-amd]

Add MiniMax-M3 FP4 MI355X Agentic Support with MTP

Adds a new single-node agentic-coding benchmark recipe for MiniMax-M3 (FP4) on MI355X using vLLM, with EAGLE3 MTP speculative decoding and DRAM-backed KV cache offloading (vllm-simple).

Changes

• New launch script: starts a vLLM server with EAGLE3 speculative decoding, AITER MoE/fusion backends, INT4 quick-reduce all-reduce, FP8 KV cache, TP/EP parallel, and optional native KV offloading to host DRAM, then runs the agentic replay/eval harness.
• New config entry minimaxm3-fp4-mi355x-vllm-agentic-mtp (image vllm-openai-rocm:nightly-cb8104839c141609d99f1254459ef3a4f1bd4263, tp=4, DRAM KV offloading via vllm-simple, spec-decoding: mtp).
• Synthetic acceptance for the throughput replay: rejection_sample_method: synthetic with synthetic_acceptance_length: 3.35, the committed MiniMax-M3 EAGLE3 golden AL for thinking_on at num_speculative_tokens=5 (golden_al_distribution/minimaxm3_eagle3.yaml), per the AgentX fairness guidelines. EVAL_ONLY accuracy runs keep real target verification, since synthetic acceptance bypasses verification and corrupts the eval score.
• Changelog entry documenting the addition (PR link TBD).

Status

Marked [WIP].

[github-actions]

Thanks for the contribution! Please reach out to respective companies' CODEOWNER to fill in the latest PR_REVIEW_CHECKLIST.md before pinging core maintainer on Slack for review. In order for the signoff PR check bot to trigger, you must follow the PR_REVIEW_CHECKLIST.md template correctly, including the phrase As a PR reviewer and CODEOWNER, I have reviewed this and have.

For PR verification, add the full-sweep-fail-fast label (strongly recommended) to this PR — the benchmark sweep only runs on labeled PRs. Use full-sweep-enabled only if you need matrix jobs to keep running past a failure.

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. See GitHub's docs on re-running failed jobs

---

感谢你的贡献！请联系相应公司的 CODEOWNER 填写最新的 PR_REVIEW_CHECKLIST.md，然后再在 Slack 上联系核心维护者进行审阅。为了触发 signoff PR 检查机器人，你必须正确遵循 PR_REVIEW_CHECKLIST.md 模板，包括保留英文语句 As a PR reviewer and CODEOWNER, I have reviewed this and have。

如需进行 PR 验证，请为此 PR 添加 full-sweep-fail-fast 标签（强烈推荐）— 基准测试 sweep 仅在带有标签的 PR 上运行。仅当需要矩阵任务在失败后继续运行时才使用 full-sweep-enabled。

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。参见 GitHub 关于重新运行失败任务的文档