Processing time is much higher with TensorRT EP than with CUDA EP #59

Open

opened

When running SuperGlue with the TensorRT Execution Provider, I see significantly higher latency compared to using the CUDA Execution Provider.

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

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests