Add new pipeline_for_v2 that loads based on ModelParams struct
Fix cli to new protocol_v2
Fix worker code to new protocol_v2
Switch to pdbplus
Split cuda_utils and normal utils
Improve readme
Improve dockerization as ipfs cli exec runs not needed anymore
Fix pyproject toml for gpu workers
Add more sections on example config
Drop and siomplify many cli commands, try to use config.ini for everything now
Use more dynamic imports on cli to speed up startup
Improve model pipelines to allow low mem cards to run big models
Add upscaler download to `skynet download` cmd