Skip to main content
Shared Hosted Training for LoRA runs has been retired. The service trained a LoRA adapter on top of a shared, multi-tenant deployment and billed per token. It no longer accepts new runs, and its .toml config format is no longer dispatched.

​
What to use instead

Hosted Training now runs on-demand: your run gets its own GPUs, every parameter is trained, and you’re billed per GPU-hour. No reserved cluster required. Configs use the native prime-rl schema rather than the old flat format — see Full Fine-Tuning for the config shape and End-to-End Run for a walkthrough.

​
Your existing adapters

LoRA adapters from completed runs remain downloadable and deployable for inference. See LoRA Adapter Deployments.
Adapter deployment works today, but is expected to change. We’ll update that page before anything does.

​
LoRA itself isn’t going away

Only the hosted shared service was retired. LoRA remains a supported, actively maintained feature of prime-rl for both RL and SFT, which you can run on your own GPUs or on a Model Factory Cluster.

Getting Started

Launch an on-demand Hosted Training run.

LoRA in prime-rl

Train LoRA adapters on your own infrastructure.