Ilker ManapandClaude Opus 5.5 c31bac8d4b An awake on-demand model survives a restart of the control plane ...

A control plane that has just started or become leader has heard no
requests, and read the on-demand replicas its nodes report as wanted by
nobody: it drained every one of them at every failover. An adopted replica
of an on-demand model now gets a whole idle timeout from its adoption.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

2026-10-10 01:10:44 +02:00

..

adopt.go

An awake on-demand model survives a restart of the control plane

2026-10-10 01:10:44 +02:00

demand.go

llmgw stop, start and restart act on the whole system

2026-10-07 18:01:45 +02:00

evict.go

Tracing beyond the router: reconcile passes, placement and a replica's start traced down to the node

2026-10-05 00:03:17 +02:00

facility_test.go

Facility-aware placement: racks, PDUs, holds and power caps

2026-10-05 01:17:49 +02:00

fetch_test.go

Carry a download's progress to where somebody is looking at it

2026-09-27 07:49:08 +02:00

headroom_test.go

Reserve CPU cores and require memory for CPU models

2026-09-30 17:43:13 +02:00

headroom.go

Facility-aware placement: racks, PDUs, holds and power caps

2026-10-05 01:17:49 +02:00

health.go

Add capacity classes and preempt lower ones to place a model

2026-09-30 18:02:59 +02:00

leadership_test.go

A standby that takes over waits for the fleet before placing

2026-10-07 13:40:28 +02:00

measured_test.go

Scale and place by what a replica was measured to serve

2026-09-30 18:21:08 +02:00

measured.go

Scale and place by what a replica was measured to serve

2026-09-30 18:21:08 +02:00

notify_test.go

Notifications: webhooks for a parked model, a lost node, a spent budget and new weights; Alertmanager receiver templates

2026-10-04 16:58:11 +02:00

preempt_test.go

Name only the replicas that would make room in headroom

2026-09-30 23:01:40 +02:00

preempt.go

Merge C20 tracing beyond the router

2026-10-05 00:05:29 +02:00

quotas_test.go

Guarantee and limit capacity per part of the tenancy tree

2026-09-30 18:15:38 +02:00

quotas.go

Guarantee and limit capacity per part of the tenancy tree

2026-09-30 18:15:38 +02:00

reconciler_test.go

An awake on-demand model survives a restart of the control plane

2026-10-10 01:10:44 +02:00

reconciler.go

llmgw stop, start and restart act on the whole system

2026-10-07 18:01:45 +02:00

replica.go

A replica says what its engine computes on, and llama.cpp's word on the CPU refuses a GPU placement

2026-10-07 13:02:17 +02:00

restart.go

A replica restarted in place keeps the room it frees for its replacement

2026-10-08 11:42:55 +02:00

schedule_test.go

Scaling by the clock: schedule windows with their own min and max, prewarm, control.timezone

2026-10-04 23:16:56 +02:00

spread_test.go

Pin down where CPU replicas land, and where they deliberately do not

2026-09-16 09:57:12 +02:00

stuck_test.go

Stop an idle model to make room for one somebody asked for

2026-09-17 17:51:07 +02:00

trace_test.go

Tracing beyond the router: reconcile passes, placement and a replica's start traced down to the node

2026-10-05 00:03:17 +02:00

trace.go

Tracing beyond the router: reconcile passes, placement and a replica's start traced down to the node

2026-10-05 00:03:17 +02:00