add direct converter for aten.repeat instead of decompo… - #4483
Open
apbose wants to merge 1 commit into
Open
Conversation
github-actions
Bot
added
component: tests
…sing it aten.repeat was decomposed via Torch's core decomposition into unsqueeze -> expand -> reshape, which doubles the tensor rank to 2N. TensorRT tensors support at most 8 dims, so this broke for any input of rank >= 5 with a confusing pybind TypeError deep in prepend_ones. Move aten.repeat to torch_disabled_decompositions and register a converter that reuses the existing aten.tile implementation (impl.slice.tile), which builds the output directly at its native rank via a WRAP-mode ISliceLayer, along with a capability_validator that falls back to PyTorch for the genuine >8-rank case instead of crashing. Fixes #3172
apbose
force-pushed
the
abose/repeat_decomposition_to_converter
branch
from
August 13, 2026 18:33
ffb1c6f to
0ab6d9f
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Addresses #3712 and #3974