Ilker ManapandClaude Opus 5.5 721705b29d A card in the wrong PCIe slot is said so ...

At the user's asking: we know what a card's link could be, so a card
linked slower is reported. Each agent reads, apart from the GPU query so
that a driver not knowing a field costs nothing else, the fastest PCIe
generation card and slot allow together, the card's own, and the lanes in
use and the card's most (nvidia-smi; NVML in the nvml build). The current
generation is not compared: it drops while a card idles. A card on fewer
lanes, or a slot of an older generation, is a node warning with the GB/s
it carries against what it could — on the dashboard, the console and in
llmgw doctor, which points at lspci's LnkCap and LnkSta. MIG instances are
said of their card. GPU proto fields 23-26.

The PoC's Quadro RTX 6000 reads Gen3 of Gen3, x16 of x16, idle at Gen1:
nothing to say.

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

2026-10-29 08:49:16 +01:00

..

actor_test.go

Reserve CPU cores and require memory for CPU models

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

adapters_test.go

Attach LoRA adapters from the command line

2026-10-01 07:30:13 +02:00

api_test.go

A card in the wrong PCIe slot is said so

2026-10-29 08:49:16 +01:00

api.go

A card in the wrong PCIe slot is said so

2026-10-29 08:49:16 +01:00

audit.go

Audit log: every change through the admin API and the administration pages, with ctl audit

2026-10-04 16:25:56 +02:00

auth_test.go

Sign-in is set up from the console, and a directory tried before it is kept

2026-10-19 12:55:27 +02:00

auth.go

Sign-in is set up from the console, and a directory tried before it is kept

2026-10-19 12:55:27 +02:00

canary.go

Merge C21 quality suites and gating

2026-10-05 00:08:33 +02:00

eval_test.go

Quality suites, and new weights held to one: ctl eval, model update/promote --eval, model gate

2026-10-05 00:04:43 +02:00

eval.go

Merge C21 quality suites and gating

2026-10-05 00:08:33 +02:00

export.go

A ComfyUI model may make meshes: from a picture, with its licence inside

2026-10-10 18:30:52 +02:00

fabrictest.go

The admin API described in OpenAPI 3.1: generated from a route table by docgen, served at /api/v1/openapi.json

2026-10-04 23:47:59 +02:00

facility_test.go

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

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

facility.go

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

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

federation.go

Federation: another llmgw cluster as a provider, its models as PEER/MODEL

2026-10-05 01:21:30 +02:00

guard_test.go

The cluster's settings live in the store, and every change takes effect

2026-10-05 15:25:23 +02:00

guard.go

How fast the judge is, measured, and said at install

2026-10-20 22:35:19 +02:00

jobs.go

G4: a page that makes 3D models, and ctl 3d

2026-10-10 19:16:20 +02:00

judges_test.go

How fast the judge is, measured, and said at install

2026-10-20 22:35:19 +02:00

judges.go

The judge check gives each judgment a text of its own

2026-10-20 22:45:58 +02:00

kb_test.go

Knowledge bases administered: llmgw ctl kb and /api/v1/kb

2026-10-08 13:49:44 +02:00

kb.go

An embedding model's query_prefix, put before questions and never before documents

2026-10-09 18:03:00 +02:00

kbdataset_test.go

Training data from a collection: llmgw ctl kb dataset

2026-10-08 20:04:37 +02:00

kbdataset.go

Trained adapters published, private to their owners like the knowledge bases they come from

2026-10-08 21:30:50 +02:00

logs.go

Show a node's logs on the admin page

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

mcp_server_test.go

The cluster as a read-only MCP server, llmgw:admin

2026-10-20 17:18:28 +02:00

mcp_server.go

The cluster as a read-only MCP server, llmgw:admin

2026-10-20 17:18:28 +02:00

mcp_test.go

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

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

mcp.go

The company's MCP servers on a web page

2026-10-28 19:26:51 +01:00

metrics.go

A btop-like monitor in the console, from Prometheus; node exporters discovered and installed

2026-10-04 01:51:05 +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

nodeengine_test.go

Give each GPU node a vLLM build it can run, chosen on the cluster page

2026-10-01 12:39:14 +02:00

notify.go

The cluster's settings live in the store, and every change takes effect

2026-10-05 15:25:23 +02:00

presets_test.go

The leader adds the picture and 3D presets a node fits, unless told not to

2026-10-13 20:48:40 +02:00

presets.go

The leader adds the picture and 3D presets a node fits, unless told not to

2026-10-13 20:48:40 +02:00

promsd_test.go

Every control plane lists the others alike to Prometheus

2026-10-15 07:53:22 +02:00

promsd.go

Every control plane lists the others alike to Prometheus

2026-10-15 07:53:22 +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

The admin API described in OpenAPI 3.1: generated from a route table by docgen, served at /api/v1/openapi.json

2026-10-04 23:47:59 +02:00

replies.go

The admin API described in OpenAPI 3.1: generated from a route table by docgen, served at /api/v1/openapi.json

2026-10-04 23:47:59 +02:00

requestbody.go

The admin API described in OpenAPI 3.1: generated from a route table by docgen, served at /api/v1/openapi.json

2026-10-04 23:47:59 +02:00

routes_test.go

The admin API described in OpenAPI 3.1: generated from a route table by docgen, served at /api/v1/openapi.json

2026-10-04 23:47:59 +02:00

routes.go

How fast the judge is, measured, and said at install

2026-10-20 22:35:19 +02:00

settings_test.go

The cluster's settings live in the store, and every change takes effect

2026-10-05 15:25:23 +02:00

settings.go

The cluster's settings live in the store, and every change takes effect

2026-10-05 15:25:23 +02:00

summary_test.go

Know where the weights are, without owning the storage

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

summary.go

llmgw stop, start and restart act on the whole system

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

system.go

llmgw stop, start and restart act on the whole system

2026-10-07 18:01:45 +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

Set capacity quotas, class, owner and reservation from the admin pages

2026-09-30 22:40:45 +02:00

tenancy_test.go

Keys' project paths written as the API takes them, Acme/ml/search

2026-10-09 06:46:12 +02:00

tenancy.go

Keys' project paths written as the API takes them, Acme/ml/search

2026-10-09 06:46:12 +02:00

train_test.go

Trained adapters published, private to their owners like the knowledge bases they come from

2026-10-08 21:30:50 +02:00

train.go

Trained adapters published, private to their owners like the knowledge bases they come from

2026-10-08 21:30:50 +02:00

weights.go

A profile may load weights of its own

2026-10-10 17:15:38 +02:00