Skip to content

Enable loading task models lazily #1215

Description

@JulienVig

Is your feature request related to a problem? Please describe.
Currently, the server instantiates all models on boot, notably it downloads the pretrained GPT-2 model from google cloud which weighs 500MiB. This caused the google server to crash and requires increasing its memory limit. It also slows down the startup time a lot.

Describe the solution you'd like
The server could lazily instantiate models when a client joins the task (the server is in charge of sending the base model to new participants).

In the case of the GPT-2 model, clients could potentially be in charge of downloading the model themselves (right now the server downloads it, serializes it and each clients downloads it from the server).

Activity

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

Metadata

Metadata

Assignees

No one assigned

    Labels

    priority-2Important but not required for productionscope-discojsRelated to Disco.jsscope-serverRelated to the servertype-reworkCode that needs to be improved

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions