Docs

How to get a model serving on hardware you control, written by the people who keep the fleet running. Every command here is one we run ourselves.

Start here

From a key pair on your laptop to a shell on a Spark.

Serving models

Turning a box with weights on it into an endpoint other software can call.

Interfaces and gateways

The layer between your endpoint and the people who will use it.

Training and tuning

When prompting has run out of road and the model needs to learn your data.

Fine-tuning

Fine-tune a model on your company's data

LoRA on 70B-class models fits in 128 GB of unified memory, with the training set staying on the node's local NVMe.

11 min read
Fine-tuning

Serving a LoRA adapter with vLLM

Hot-swapping adapters on one base model, and when a merged checkpoint is the better answer.

coming soon

Choosing hardware

Whether this machine is the right one, argued honestly.

Background reading

Longer arguments about why any of this is worth doing on your own hardware.

Something missing?

If you hit a wall these docs did not cover, tell us and we will write it up. The gaps our customers find are the ones worth filling first.

Deploy a Spark Request a guide