Repository navigation
[Bug][Fix] Handle concatenation of 1D empty tensors with higher-dimensional tensors - #20762
Open
Netra-Srinivasan-McW wants to merge 1 commit into
Open
Netra-Srinivasan-McW wants to merge 1 commit into
Netra-Srinivasan-McW wants to merge 1 commit into
Conversation
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Issue
PyTorch supports concatenating a 1D empty tensor (shape
(0,)) with a higher-dimensional tensor. On the other hand, TVM Relax raises an error when the input tensors have different numbers of dimensions.This issue occurs in models such as Perplexity AI's pplx-embed-v2-late-9b, where the KV cache is initially represented as a 1D empty tensor. Concatenating it with higher-dimensional key/value tensors causes the Relax frontend conversion to fail.
Solution
This PR updates the Relax frontend to handle concatenation of a 1D empty tensor with a higher-dimensional tensor, enabling model execution to proceed without this error.
Closes #20761.