Convert torch.cond to TensorRT IIfConditional - #4657
Open
micwill755 wants to merge 1 commit into
Open
Conversation
Keep both branches in one TRT engine when the predicate and subgraphs are convertible, instead of partitioning cond back to PyTorch.
github-actions
Bot
added
component: tests
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
torch.ops.higher_order.cond/torch.condto TensorRTIIfConditionalso the predicate and both branches stay in one TRT engine instead of falling back to PyTorch.condin PyTorch.get_attr, and convert each branch in the existing network via a subgraph interpreter.Fixes #3923
Test plan
tests/py/dynamo/conversion/test_cond_aten.py(add/sub, 1-element pred, multi-output, clone pass-through, Linear outside cond, nested cond)tests/py/dynamo/models/test_cond.py(converter membership, unsupported-op fallback,require_full_compilation=Truee2e for both pred values)