fix: support MiniMax-M3 pipeline parallelism in PD disaggregation

[shiyang814-cpu]

• Preserve global sparse layer IDs for MiniMax index-K state registration.
• Map sparse index transfer entries by global layer ID under pipeline parallelism.
• Normalize scattered PP proxy tensors during Decode CUDA Graph capture.
• Add regression tests for sparse state registration and PP proxy shapes.
• Verified with TP4/PP2/EP4 on two 8×H20 nodes using Mooncake PD.
• Decode CUDA Graph replay confirmed with batches [4, 8].

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.
• Follow the SGLang code style guidance.

Review and Merge Process

1. Ping Merge Oncalls to start the process. See the PR Merge Process.
2. Get approvals from CODEOWNERS and other reviewers.
3. Trigger CI tests with comments or contact authorized users to do so.
   • Common commands include /tag-and-rerun-ci, /tag-run-ci-label, /rerun-failed-ci
4. After green CI and required approvals, ask Merge Oncalls or people with Write permission to merge the PR.

---

CI States

Latest PR Test (Base): ❌ Run #32647732433
Latest PR Test (Extra): ❌ Run #32647732272
Latest PR Test (AMD ROCm 7.2): ❌ Run #32647732378