Skip to content

Facing issues while deploying large models.  #25

@sanjay-nit

Description

@sanjay-nit

Facing issues while deploying LLM models.
After an hour of starting, It was able to build the Docker image and also push it.

Getting timed out Error while deploying

Is there any resource constraint or anything else that I should follow while deploying large models?
Below is the last few lines from build logs

Image pushed.
SUCCESS: Model Registered
Deploying...
ERROR: timed out waiting for deployment to be healthy

FYI: I'm hosting Falcon-40b LLM hugging face model.

cc: @sanjayk1801

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions