You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Disaggregated / decode-node handoff must transfer paged block tables and pool blocks, not dense snapshots, once the unified store is the source of truth.
Tasks
Extend src/distributed/kv_cache_serde/ to serialize PagedSequenceState block tables plus the referenced pool blocks (and Turbo sidecars) and restore them via PagedBlockPool::restore_sequence.
Validate a prefill-node to decode-node handoff reconstructs identical KV and identical first-token logits.
Confirm refcount and block ownership are correct after restore (no double-free, no leak).
Acceptance criteria
A disaggregated run reproduces single-node output within tolerance using the paged block-transfer path.
Block accounting after restore matches the originating node.
Context
Disaggregated / decode-node handoff must transfer paged block tables and pool blocks, not dense snapshots, once the unified store is the source of truth.
Tasks
src/distributed/kv_cache_serde/to serializePagedSequenceStateblock tables plus the referenced pool blocks (and Turbo sidecars) and restore them viaPagedBlockPool::restore_sequence.Acceptance criteria
Dependencies
Blocked by Phase 4 (unification).
Part of #116