Skip to content

Conversation

@carlosgjs
Copy link

@carlosgjs carlosgjs commented Oct 20, 2025

Counterpart to RolnickLab/antenna#987 for an e2e implementation of the "pulling" (v2) processing service.

Adds ami worker that runs a worker that polls an antenna service for job tasks, processes them and posts back the result. Use:

export ANTENNA_API_TOKEN=<token>
ami worker  # currently defaults to localhost:8000

@carlosgjs carlosgjs changed the title WIP: Worker implemention for PyTorch models Worker implemention for PyTorch models Oct 24, 2025
@carlosgjs carlosgjs marked this pull request as ready for review October 24, 2025 19:43
@carlosgjs carlosgjs changed the title Worker implemention for PyTorch models Worker implementation for PyTorch models Oct 24, 2025
)


# @TODO This requires loading all models into memory! Can we avoid this?
Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Moved this to the fastapi initialization to we don't pay the cost when running ami worker

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant