Ilker ManapandClaude Opus 5.5 78e41460f9 Scale and place by what a replica was measured to serve ...

Stored ctl bench results reach the reconciler: requests per replica past
the measured SLO concurrency scale a model up, a replica is taken back only
if the rest stay under 70% of theirs, and among profiles of equal priority
the most measured tokens per GPU or core is tried first. ctl model target
sizes a model for a throughput against the room there is.

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

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

..

actor_test.go

Reserve CPU cores and require memory for CPU models

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

api_test.go

Guarantee and limit capacity per part of the tenancy tree

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

api.go

Scale and place by what a replica was measured to serve

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

fabrictest.go

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

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

logs.go

Show a node's logs on the admin page

2026-09-28 12:27:47 +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

summary_test.go

Know where the weights are, without owning the storage

2026-09-17 08:21:16 +02:00

summary.go

Park a model that fails every time it starts, and say so everywhere

2026-09-30 01:21:57 +02:00

target_test.go

Scale and place by what a replica was measured to serve

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

target.go

Scale and place by what a replica was measured to serve

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

weights.go

Refuse a node with no room, and take back only what llmgw put there

2026-09-18 09:51:05 +02:00