Add Kimi-K2.5 MXFP4 PD disaggregation recipe and update configurations

[Jasen2201]

Motivation

Technical Details

Test Plan

Test Result

Submission Checklist

• Look over the contributing guidelines at https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.

[github-actions]

🏷️ CI Guide

Runs automatically on every eligible PR before approval:

• ✅ Pre Checkin: Black, Ruff, catalog schema validation, non-GPU unit tests

Heavy model tests:

• ✅ Run after the PR is approved and Pre Checkin passes
• ✅ Run immediately when an approval review is submitted
• ✅ Can be requested before approval with labels

Label	Tests
ci:full	Run all heavy PR model tests: native ATOM, vLLM, and SGLang
ci:atom	Run native ATOM model accuracy tests
ci:vllm	Run ATOM vLLM OOT model accuracy tests
ci:sglang	Run ATOM SGLang model accuracy tests

Heavy jobs are skipped when the PR is not approved and no matching ci:* label is present.
Add labels via the sidebar or gh pr edit 1575 --add-label <label>

[Copilot]

Pull request overview

Adds a new mesh recipe documenting how to run Kimi-K2.5 (MXFP4) in a 1P+1D prefill/decode-disaggregated setup using ATOM + Mooncake KV transfer + atomesh routing.

Changes:

• Added a single-node (8-GPU) PD-disaggregation serving recipe for amd/Kimi-K2.5-MXFP4.
• Included verification (curl), GSM8K accuracy (lm_eval), and serving benchmark commands via the atomesh router.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated 2 comments.

[Copilot]

Copilot was unable to review this pull request because the user who requested the review is ineligible. To be eligible to request a review, you need a paid Copilot license, or your organization must enable Copilot code review.