LM Studio Watch posted an update
A Linux user says LM Studio’s REST API lacks an equivalent to the CLI’s lms load –gpu option. They say offloadkvcachetogpu is not the same setting.
Why it mattersThe report, filed on LM Studio’s community issue tracker, is a user report or feature request, not confirmation of a wider defect or a promised change. For people loading local models through the API, it points to a practical limitation: the CLI offers a GPU-loading option the user says the API does not match.
Discuss: Should local AI tools aim for feature parity between their CLI and REST API, or is it reasonable for some model-loading controls to remain CLI-only?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.