Ilker ManapandClaude Opus 5.5 8a76a53afb The control plane uses whichever mirror answers ...

mirror.peers names the mirrors kept in step with mirror.api. The
mirror's management calls go to the first that can be reached, and
each mirror is asked every fifteen seconds whether it answers: a shard
is sent its model's and adapters' address on one that does while the
mirror the catalog names is down.

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

2026-10-29 13:43:27 +01:00

..

agentsettings_test.go

The nodes' agent settings kept with the cluster's, agent.yaml down to what an agent needs to start

2026-10-08 18:06:36 +02:00

agentsettings.go

The nodes' agent settings kept with the cluster's, agent.yaml down to what an agent needs to start

2026-10-08 18:06:36 +02:00

controlplanes.go

Add a standby control plane with server add, and draw the screens as windows

2026-10-03 22:29:12 +02:00

convert_test.go

The control plane uses whichever mirror answers

2026-10-29 13:43:27 +01:00

convert.go

The control plane uses whichever mirror answers

2026-10-29 13:43:27 +01:00

firewall.go

llmgw stop, start and restart act on the whole system

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

heartbeat_test.go

The memory is measured after the agent reaches its control plane

2026-10-27 15:31:21 +01:00

identity_test.go

Revoke a removed node's certificate, and require --api-client with a mirror's mutual TLS

2026-10-04 10:34:35 +02:00

identity.go

Revoke a removed node's certificate, and require --api-client with a mirror's mutual TLS

2026-10-04 10:34:35 +02:00

installable_test.go

Offline sites and Kubernetes: llmgw bundle create, import and trust, offline.mirror, server init --bundle; a Helm chart for the control plane

2026-10-05 00:13:39 +02:00

kv_test.go

Precise KV-index routing: vLLM KV cache events through the agent, routed by leading blocks held

2026-10-05 01:21:11 +02:00

kv.go

Precise KV-index routing: vLLM KV cache events through the agent, routed by leading blocks held

2026-10-05 01:21:11 +02:00

mig_test.go

MIG: a card in MIG mode is placed as its instances, each a GPU of class <card>-mig-<profile>

2026-10-05 00:01:14 +02:00

service.go

The memory is measured after the agent reaches its control plane

2026-10-27 15:31:21 +01:00

train.go

LoRA adapters trained on the nodes: llmgw ctl train

2026-10-08 20:25:57 +02:00