Ilker ManapandClaude Opus 5.5 0e73f37128 Stop only the replicas that make the room ...

Candidates were added in order until the model fitted, and every one added
was stopped, including those tried first that freed room on the wrong node.
A set that works is now pruned to the replicas it needs.

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

2026-09-30 18:21:58 +02:00

..

adminapi

Scale and place by what a replica was measured to serve

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

agentsvc

Reserve CPU cores and require memory for CPU models

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

catalog

Guarantee and limit capacity per part of the tenancy tree

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

fabrics

Watch each fabric's subnet managers, and keep a fabric one through a failover

2026-09-29 07:47:03 +02:00

fabrictest

Measure two nodes' fabric rail by rail: llmgw ctl fabric-test

2026-09-29 21:29:23 +02:00

fleetmetrics

Guarantee and limit capacity per part of the tenancy tree

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

inventory

Reserve CPU cores and require memory for CPU models

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

modelserve

Reserve CPU cores and require memory for CPU models

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

modelsvc

Guarantee and limit capacity per part of the tenancy tree

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

nvlink

Find multi-node NVLink domains, place across them, and show them as racks

2026-09-29 09:07:59 +02:00

placement

Reserve CPU cores and require memory for CPU models

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

quota

Guarantee and limit capacity per part of the tenancy tree

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

reconciler

Stop only the replicas that make the room

2026-09-30 18:21:58 +02:00

topology

Map every InfiniBand fabric, draw it, and place replicas by it

2026-09-29 08:46:23 +02:00

control_test.go

Give every engine a key only the router holds

2026-09-30 00:38:29 +02:00

control.go

Guarantee and limit capacity per part of the tenancy tree

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

leadership.go

Stop a second control plane from placing work behind the first's back

2026-09-25 18:24:06 +02:00

quotas.go

Scale and place by what a replica was measured to serve

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