Skip to content

Re-evaluate utility of IaaS #501

Description

@wbenoit26

The IaaS setup makes sense on LDG, where we have at most 8 GPUs per node and none of any consequence in the condor pool. As we look to do inference on other clusters with more GPUs distributed over multiple nodes (OSG, Delta), it's not clear to me that this setup is still advantageous (particularly for OSG, where communication across nodes doesn't seem possible). We should benchmark throughput with just loading the model in-process.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions