Ilker ManapandClaude Opus 5.5 c3a75dcf3f A node being lent says when a replica with nowhere to go is stopped ...

Tried on the PoC: lending cuda01, the one GPU node, its model had nowhere
else to go and waited out the drain's five-minute grace, while ctl slurm
status said only "1 replica(s) still to move off". It now says the time
that replica is stopped at. Also recorded: Slurm on a GPU node, tried on
cuda01 (gres, ConstrainDevices, accounting of gres/gpu).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-11-14 20:45:57 +01:00

..

admin-api.md

Organizations, teams, projects, keys and memberships in the admin API

2026-10-08 22:42:43 +02:00

admin-api.openapi.json

A node being lent says when a replica with nowhere to go is stopped

2026-11-14 20:45:57 +01:00

choosing-models.md

Manage people and the tenancy tree, from the web and the CLI

2026-09-28 16:26:39 +02:00

client-api.openapi.json

The gateway embeds the documents llmgw-kb sends as text

2026-10-29 21:56:05 +01:00

clients.md

Company MCP servers are registered with ctl mcp, and tools granted with keys limits --tools

2026-10-20 12:50:55 +02:00

console.md

Status says when the cluster's alerts go nowhere

2026-11-12 22:49:37 +01:00

data.md

Answers to similar questions, not only the same one

2026-10-25 17:47:11 +01:00

development.md

Docs: one way in — quick-install starts at the setup screens, quickstart becomes development, install.md no longer says engines are yours to install

2026-10-04 17:32:54 +02:00

fabrics.md

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

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

facility-aware-placement.md

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

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

guardrails.md

Guardrail services merged the stricter way; the request log keeps no restored value

2026-10-29 11:03:57 +01:00

install.md

Slurm users reach a node only through a job of theirs

2026-11-14 20:30:49 +01:00

knowledge.md

The gateway embeds the documents llmgw-kb sends as text

2026-10-29 21:56:05 +01:00

kong.md

llmgw and Kong, written down after trying Kong 3.9 in front

2026-10-25 16:55:22 +01:00

kubernetes.md

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

large-models.md

A big model's download no longer runs out its startup timeout

2026-10-20 09:45:31 +02:00

llmgw-intro.pdf

The introduction's comparison on one slide

2026-11-04 17:06:49 +01:00

node-onboarding.md

Add a node with one command: llmgw node add, with a terminal screen

2026-09-29 19:33:47 +02:00

onboarding.md

An organization's admin, and forms only for those who may send them

2026-11-08 11:38:06 +01:00

quick-install.md

How fast a model would answer on the cards, as this cluster would lay it out

2026-10-28 00:19:36 +01:00

reference.md

Slurm users reach a node only through a job of theirs

2026-11-14 20:30:49 +01:00