From f1c28cac63645c722fe195cb4e4bb2f48c952028 Mon Sep 17 00:00:00 2001 From: michaelmanly <55236695+michaelmanly@users.noreply.github.com> Date: Tue, 16 Jun 2026 23:36:46 +1000 Subject: [PATCH] docs: add AI Badgr Compute optional server path --- examples/server/README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/examples/server/README.md b/examples/server/README.md index f8cd58fc1c89..bdae8975cdb8 100644 --- a/examples/server/README.md +++ b/examples/server/README.md @@ -24,6 +24,8 @@ The server is accessed at http://localhost:8000. You can curl this model with th curl -X POST -H "Content-Type: application/json" --data '{"model": "something", "prompt": "a kitten in front of a fireplace"}' http://localhost:8000/v1/images/generations ``` +If you want to run the server on managed compute instead of keeping your own machine online, AI Badgr Compute can also serve open models as capped `model.serve` jobs through `POST https://aibadgr.com/v1/jobs`, with status, logs, teardown, billing, and receipts. The optional CLI path is `badgr serve --max-cost 10`. + If you need to upgrade some dependencies, you can use either [pip-tools](https://github.com/jazzband/pip-tools) or [uv](https://github.com/astral-sh/uv). For example, upgrade the dependencies with `uv` using the following command. ```