agentic-pd-hybrid

Files

Claude Code Agent dc4867c270 feat(snapshot): D→P RDMA link Phase 1 — minimal byte transport

A thin wrapper around mooncake.engine.TransferEngine that does
one-sided RDMA writes between two SnapshotPeer endpoints. Bypasses
SGLang's MooncakeKVManager (which is hard-gated to PREFILL/DECODE
roles via add_transfer_request assertion at conn.py:1563) so the
D→P direction doesn't require invasive role-axis changes upstream.

Smoke test (two subprocess.Popen processes, mlx5_60, 127.0.0.1):
  1 KB    9.0 ms   (one-time openSegment handshake)
  16 KB   0.04 ms  3.5 Gbps
  1 MB    0.10 ms  82 Gbps
  16 MB   0.58 ms  232 Gbps
  64 MB   1.70 ms  316 Gbps   (~80% of NDR 400G line rate)

All 5 sizes pass SHA256 verification end-to-end.

Files:
  src/agentic_pd_hybrid/snapshot_link.py — SnapshotPeer, SnapshotEndpoint
  scripts/snapshot_link_receiver.py      — child-process receiver
  scripts/smoke_snapshot_link.py         — sender + verifier
  docs/D_TO_P_PHASE1_LINK_ZH.md          — phase 1 acceptance doc

Next: Phase 2 (D-side scheduler commit hook), Phase 3 (P-side prefill
bypass with snapshot KV). See docs/D_TO_P_SYNC_DESIGN_ZH.md §5.

2026-05-13 00:55:55 +08:00

archive

docs: archive deprecated docs to docs/archive/, drop E1 from onboarding

2026-05-11 22:40:35 +08:00

figures

fix(figures): GPU utilization figure annotation/headroom polish

2026-05-11 22:28:39 +08:00

D_TO_P_PHASE1_LINK_ZH.md

feat(snapshot): D→P RDMA link Phase 1 — minimal byte transport

2026-05-13 00:55:55 +08:00

D_TO_P_SYNC_DESIGN_ZH.md

docs(design): D→P RDMA snapshot push design