TensorRT icon indicating copy to clipboard operation
TensorRT copied to clipboard

feat: Add module_call_graph to handle output spec

Open peri044 opened this issue 1 year ago • 0 comments

Description

  • This PR adds module_call_graph to preserve the output spec obtained from the graph module.
  • This will let exported program know what the output_spec is during it's construction and ensure the verifier operates properly.
  • This PR should go after https://github.com/pytorch/pytorch/pull/120361 so that the codegen of the partitioned module is populated correctly to add pytree flatten/unflatten nodes accordingly

Type of change

Please delete options that are not relevant and/or add your own.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)

Checklist:

  • [x] My code follows the style guidelines of this project (You can use the linters)
  • [x] I have performed a self-review of my own code
  • [ ] I have commented my code, particularly in hard-to-understand areas and hacks
  • [ ] I have made corresponding changes to the documentation
  • [x] I have added tests to verify my fix or my feature
  • [x] New and existing unit tests pass locally with my changes
  • [ ] I have added the relevant labels to my PR in so that relevant reviewers are notified

peri044 avatar Feb 22 '24 00:02 peri044