llmgw

239 Commits 9 Branches 95 Tags

3 Commits

Include renames

Author	SHA1	Message	Date
Ilker ManapandClaude Opus 5.5	4d9284ce9f	Find each node's management interface, and lift the agent's memlock limit The agent's defaults said eth0 before normalize looked for the interface holding the management address, so it never looked: a node on ens3 or bond0 had NCCL and Gloo bootstrap over an interface it does not have. It is now found, with eth0 only as the last resort. The agent unit sets LimitMEMLOCK=infinity. RDMA pins what it registers, and under systemd's 8 MB default an engine without the capability that lets root ignore the limit fails its first collective over InfiniBand. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>	2026-09-29 01:44:59 +02:00
Ilker ManapandClaude Opus 5	afb3797e57	Document the mirror that exists rather than the one you assemble The page described nginx and a curl loop, which was accurate when the mirror was a directory somebody kept by hand. It is a subcommand now, so it says so: the two listeners and why they are two, the API and what each endpoint answers, and the certificates coming from the authority the fleet already has. nginx stays, further down. It serves a directory perfectly well and anyone already running it should not be told to install something to replace it. The systemd unit spells out --base in a comment because it is the flag that goes wrong quietly: it ends up in catalog entries, and a wrong one makes `mirror unused` call files unreferenced while they are in use. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>	2026-09-27 09:43:02 +02:00
Ilker ManapandClaude Opus 5	555e4678cb	Ship the systemd units, and stop the plan lying about what is done CI / test (push) Successful in 1m16s Details Phase 3 had a block duplicated into itself, including an unchecked 'EndpointSource becomes dynamic' sitting directly under the checked line saying it was wired. Several phase 5 items had shipped without being ticked. The units were only ever on the machines and in a scratch directory, which makes them undocumented operational knowledge rather than part of the project. KillMode=process in particular is not obvious and not optional: without it systemd takes the engines down with the agent, turning a thirty-second upgrade into a model reload on every node. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>	2026-09-16 10:04:44 +02:00

Author

SHA1

Message

Date

Ilker ManapandClaude Opus 5.5

4d9284ce9f

Find each node's management interface, and lift the agent's memlock limit

The agent's defaults said eth0 before normalize looked for the interface
holding the management address, so it never looked: a node on ens3 or
bond0 had NCCL and Gloo bootstrap over an interface it does not have. It
is now found, with eth0 only as the last resort.

The agent unit sets LimitMEMLOCK=infinity. RDMA pins what it registers,
and under systemd's 8 MB default an engine without the capability that
lets root ignore the limit fails its first collective over InfiniBand.

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

2026-09-29 01:44:59 +02:00

Ilker ManapandClaude Opus 5

afb3797e57

Document the mirror that exists rather than the one you assemble

The page described nginx and a curl loop, which was accurate when the mirror
was a directory somebody kept by hand. It is a subcommand now, so it says so:
the two listeners and why they are two, the API and what each endpoint answers,
and the certificates coming from the authority the fleet already has.

nginx stays, further down. It serves a directory perfectly well and anyone
already running it should not be told to install something to replace it.

The systemd unit spells out --base in a comment because it is the flag that
goes wrong quietly: it ends up in catalog entries, and a wrong one makes
`mirror unused` call files unreferenced while they are in use.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-09-27 09:43:02 +02:00

Ilker ManapandClaude Opus 5

555e4678cb

Ship the systemd units, and stop the plan lying about what is done

CI / test (push) Successful in 1m16s

Details

Phase 3 had a block duplicated into itself, including an unchecked
'EndpointSource becomes dynamic' sitting directly under the checked line
saying it was wired. Several phase 5 items had shipped without being ticked.

The units were only ever on the machines and in a scratch directory, which
makes them undocumented operational knowledge rather than part of the project.
KillMode=process in particular is not obvious and not optional: without it
systemd takes the engines down with the agent, turning a thirty-second upgrade
into a model reload on every node.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-09-16 10:04:44 +02:00