Commit Graph
10 Commits
Author SHA1 Message Date
Ilker ManapandClaude Opus 5.5 a1b1663e9d A btop-like monitor in the console, from Prometheus; node exporters discovered and installed
Monitor draws CPU, memory, GPUs, requests, tokens, latency, network and disk
as Braille charts over 5m/1h/24h/7d, then per node, card and model
sparklines; node and model pages have their own. History is read from
monitoring.prometheus through POST /api/v1/metrics/range, or without it
from what the console saw. The control plane serves the cluster's machines
for Prometheus http_sd at /prometheus/targets on its metrics port, and node
add installs prometheus-node-exporter.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 01:51:05 +02:00
Ilker ManapandClaude Opus 5.5 e12996f7dd Serve and update models in the background from the console, and follow them under Jobs
The console starts a serve or update job over the admin API and stays,
instead of closing to follow the download. Jobs lists them with their
progress and steps; the sidebar counts those running. ctl model serve and
update take --detach; ctl jobs lists jobs and follows one.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 01:27:02 +02:00
Ilker ManapandClaude Opus 5.5 54db7aecb7 Plan a repository's files against the fleet, and serve the one that suits it the way it fits
The control plane reads the model's shape from one GGUF header or its
config.json and lists, for every file, the best way it runs here: one card,
several of a node's (by layer for llama.cpp, tensor-parallel for vLLM),
several nodes' over one fabric (vLLM, pipeline-parallel between them), or a
CPU node; what each card holds and whether it is free now. ctl model plan
prints it; model serve takes its file and way unless told, gives a GGUF on
GPUs a GPU profile, and with --fallbacks adds the next best ways. The
console shows it per file and asks for the way and the fallback.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 01:03:48 +02:00
Ilker ManapandClaude Opus 5.5 a16097cfe8 Serve vision models with their projector and original weights on vLLM; group the mirror by version
model serve takes --projector, fetched beside the weights and loaded by
llama.cpp with --mmproj, and --format safetensors with --gpu-class and --tp,
which fetches the weights with their config and tokenizer and runs them on
vLLM. The console offers both, F switching between GGUF and original
weights. The mirror view is one row per version with its files on Enter.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 00:42:59 +02:00
Ilker ManapandClaude Opus 5.5 dac7ff0e99 The manual in the binary: llmgw docs, and Help in the console
Every document and a page for every command, built from their help, read
like info: topics, contents, find. ? opens the console's own page, which is
new and covers every screen.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 00:19:50 +02:00
Ilker ManapandClaude Opus 5.5 44425193bd Track the registry's new weights for served models, and move a model to them or back
A model served from the registry records its origin: repository, commit and
each file's checksum; one served before is worked out from the mirror's
record of where it fetched the file. Every mirror.update_check (6h) the
control plane asks whether those files changed there. ctl model updates
lists it, ctl model update fetches beside the old files, checks, swaps and
replaces replicas one at a time, ctl model rollback goes back. The console
shows it on Models and offers the same.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 00:12:20 +02:00
Ilker ManapandClaude Opus 5.5 2bf43ed90c Search Hugging Face from the console and serve what is found
Serve a model is a view of the registry's GGUF models, trending or searched;
Enter on one lists its files, and the one chosen is served with
llmgw ctl model serve. A form of one field is applied by Enter on it.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-03 23:44:51 +02:00
Ilker ManapandClaude Opus 5.5 eb7dac8a67 The console manages people, keys, organizations and the mirror, and scrolls a tall sidebar
Accounts, API keys and Organizations views read the store and change it by
running the users, keys and org commands in-process, so their checks and
messages are the ones shown. A Mirror view lists what the mirror holds and
which models use it, downloads into it and removes from it. Models gain
adding from a definition file.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-03 23:30:24 +02:00
Ilker ManapandClaude Opus 5.5 c7d5ee16b5 Act on the console's rows: scale, class, owner, resources, adapters, restart, remove; cordon, drain, engines, upgrade; quotas; cluster tasks
Enter on a row of Models, Nodes or Replicas opens what can be done to it,
as forms and questions over the admin API. A Quotas view sets and clears
capacity quotas. Do gains serving a model, upgrading the cluster,
restarting every replica and a backup.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-03 23:23:12 +02:00
Ilker ManapandClaude Opus 5.5 9ab93a0aa6 Watch the cluster and edit every setting from the console
The console gains live views of nodes, GPUs, models, replicas, usage and
agent logs, and a settings tree over every key of server.yaml (agent.yaml on
a node), generated from the configuration structs: values with their
defaults and doc comments, edited in dialogs, saved only once the service's
own loader accepts them, comments kept. The generator now tells blocks apart
by package, which brings the TLS, engine and supervisor settings back into
the reference.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-03 22:54:09 +02:00