Gahow Wang a2f2645fda PD_DISAGG_RESULTS §6.3: producer hot-pinning figure ...

Direct per-producer KV-pool evidence for the session-affinity backfire.
At the same 4P+4D ratio:
- round-robin: 4 producers within 1pp of each other (spread 0pp, CV 0.01)
- session-affinity: spread 49pp (one producer ~93%, another 45%; CV 0.25)

A 25x jump in producer load imbalance — heavy multi-turn sessions
concentrate onto single producers, the same hot-pinning pathology as
sticky routing in the colocated §3.3 study.

plot_producer_hotspot.py: reduce (numpy, per-producer KV timeline from
snapshots, runs on the serving host) + plot (matplotlib, 2-panel rr vs
session comparison) — same two-stage pattern as aggregate_mb5.py.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-29 00:38:20 +08:00

271 KiB

1800x600px

Raw Permalink History