Skip to content

fix: Add check to ensure einsum converter has no more than 2 tensor inputs #1439

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 3, 2022
Merged

fix: Add check to ensure einsum converter has no more than 2 tensor inputs #1439

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
de9bdf6
fix: Add check to ensure einsum converter has correct args
gs-olive Nov 2, 2022
240db32
Add escaped quotes so user can copy-paste printed solution
gs-olive Nov 2, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions core/conversion/converters/impl/einsum.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,13 @@ auto einsum_registrations TORCHTRT_UNUSED = RegisterNodeConversionPatterns().pat
auto equation = args[0].unwrapToString();
auto in = args[1].IValue()->toListRef();

TORCHTRT_CHECK(
in.size() <= 2,
"TensorRT currently supports up to 2 input tensors "
<< "to einsum but operation had " << in.size()
<< " input tensors, please specify torch_executed_ops=[\"aten::einsum\"] "
<< "at compilation time to avoid this error.");

std::vector<nvinfer1::ITensor*> tensors;

// Populate vector of ITensor pointers
Expand Down