exo
exo copied to clipboard
Separate out the Runner's behaviour into a "connect" phase and a "load" phase
Motivation
We should ensure all runners are connected before loading the model - this gives us finer grained control in the future for the workers planning mechanism over the runners state.
Changes
- Introduced task ConnectToGroup, preceeding LoadModel
- Introduced runner statuses Idle, Connecting, Connected
- Separated out initialize_mlx from shard_and_load
- Single instances never go through the connecting phase
Test Plan
None right now.