Ilker ManapandClaude Opus 5.5 2d14918b99 An adopted engine that turns ready after registration is reported ...

The registration carries each shard's state as it is then. An adopted
engine is health-checked after that, and nothing reported the ready that
followed, so when the agent registered first the control plane kept the
replica starting while it served. After llmgw restart on the PoC two
replicas stayed so, one the only replica of qwen2.5-coder-14b. The
session's watcher now reports every shard the registration called not
ready once it is.

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

2026-10-07 19:43:13 +02:00

..

discovery

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

engines

What a shard computes on survives the agent's and the control plane's restarts

2026-10-07 13:51:40 +02:00

provision

Merge C18 offline bundles and the Helm chart

2026-10-05 00:15:47 +02:00

supervisor

An adopted engine's state is written without its command; engine-check finds the installed build

2026-10-07 14:26:28 +02:00

weights

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

agent_test.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

agent.go

An adopted engine that turns ready after registration is reported

2026-10-07 19:43:13 +02:00

bindaddr_test.go

Have engines listen on the management address, and take SGLang's key off its command line

2026-10-04 10:36:42 +02:00

config.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

controlplanes_test.go

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

2026-10-03 22:29:12 +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

disabled_test.go

Decide engines per node, and let a node join without one it cannot run

2026-10-01 12:07:25 +02:00

fabrics.go

Release v0.10.4: CPU threads, tracing, and the rest of the review

2026-09-30 04:00:35 +02:00

failover_test.go

Two control planes: a failover in seconds, and the console to set one up

2026-10-05 02:17:51 +02:00

firewall_test.go

The firewall turns off and on with the cluster's settings; llmgw wipe

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

firewall.go

The firewall turns off and on with the cluster's settings; llmgw wipe

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

gpucheck_test.go

What a replica computes on comes from nvidia-smi; llama.cpp says its layers only at -lv 4

2026-10-07 14:04:08 +02:00

gpucheck.go

What a replica computes on comes from nvidia-smi; llama.cpp says its layers only at -lv 4

2026-10-07 14:04:08 +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

logring_test.go

Show a node's logs on the admin page

2026-09-28 12:27:47 +02:00

logring.go

Show a node's logs on the admin page

2026-09-28 12:27:47 +02:00

logs.go

Release v0.10.4: CPU threads, tracing, and the rest of the review

2026-09-30 04:00:35 +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

mtls_test.go

Let an agent find the leader instead of being told one address

2026-09-25 19:30:06 +02:00

provision.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

removeweights_test.go

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

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

selfdescribe_test.go

Install a node's engines on the node, instead of trusting what is there

2026-09-28 10:59:59 +02:00

servers_test.go

Let an agent find the leader instead of being told one address

2026-09-25 19:30:06 +02:00

shutdown_test.go

Fix an agent that could neither explain itself nor stop

2026-09-16 08:03:21 +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

upgrade_test.go

Install only releases signed with the key built in; fetch a node's release on the control plane

2026-10-04 09:48:03 +02:00

upgrade.go

Release v0.10.4: CPU threads, tracing, and the rest of the review

2026-09-30 04:00:35 +02:00

watchexits_test.go

An adopted engine that turns ready after registration is reported

2026-10-07 19:43:13 +02:00