Make the model mirror a file you can copy, not an idea you have to have
CI / test (push) Successful in 1m39s

"Set up a local mirror" was advice. This is the nginx config, the directory
layout and the reason the layout has a date in it — a repository that changes
upstream changes what you are running, and the first sign is a prompt that
worked last week answering differently this week.

It says what the mirror is not, because both mistakes are easy. It is not a
caching proxy: nothing populates it on demand, deliberately, since a mirror
that reaches the internet at the least convenient moment fails in a way that
looks like llmgw being broken. And it is not needed at all if you already run
a shared filesystem — put the models there, use a path, and nothing is fetched.

It also says when a mirror stops being enough, and that llmgw is positioned to
distribute between nodes because it already knows which of them hold which
weights. That is not built, and the page says so rather than implying it is
coming.

Every behaviour it relies on was checked against the source: an http:// source
is fetched and a path is not, a killed download resumes, a partial file is
never visible under the model's name, and a shared filesystem is not counted
once per node.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5 committed 2026-09-27 08:20:50 +02:00
1 parent b7a97468e0
commit e86457cf02
3 files changed
+114 -1

No files matched your search

+2 -1
View File
@@ -108,7 +108,8 @@ throughput alone overstates what the hardware can serve.
## Where the weights live
The single highest-value piece of infrastructure here is **a local mirror**: one
internal HTTP server holding the model files. Hugging Face is slow, rate
internal HTTP server holding the model files. [deploy/mirror/](../deploy/mirror/)
has the nginx config and the directory layout. Hugging Face is slow, rate
limited, and blocked outright on plenty of corporate networks. Eight nodes each
pulling forty gigabytes from the internet is a day; from a mirror on the same
switch it is minutes. Point a model's `source` at it and llmgw fetches from