fix(gms/sglang): preserve cache ownership through recovery

[hutm]

Summary

Keep SGLang page ownership, CPU-retention state, and the native cache index coherent while persistent pages are adopted.

Why this is needed

Recovery must not expose a page to native eviction or reuse before its ownership and reconstructed index entry agree.

Validation

• The cumulative publication tip is byte-identical to the locally validated implementation.
• Cumulative focused validation: 994 passed, 1 skipped; the later vLLM-focused rerun passed 244 tests.
• Local TP2 crash tests passed exact-output recovery for vLLM and SGLang; final performance qualification remains tracked in DEP: Production hardening for persistent GMS KV failover #15035.
• This draft checkpoint still requires normal CI and reviewer validation before merge.

Stack

• Part 14 of 15 in the production-hardening train.
• Draft DEP and complete review order: DEP: Production hardening for persistent GMS KV failover #15035.
• Base: hutm/gms-hardening-13-sglang-reservations.

This PR is intentionally draft and stacked on its immediate predecessor.

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.