We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
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
ttnn.moreh_norm
Describe the bug When dim is not the last dimension (-1), accuracy of ttnn.moreh_norm drops.
dim
To Reproduce Steps to reproduce the behavior:
aten.linalg_vector_norm
pytest tests/lowering/reduction/test_vector_norm.py --runxfail
FAILED tests/lowering/reduction/test_vector_norm.py::test_vector_norm[input_shape1-2-2] - AssertionError: 0.9977884821398946 FAILED tests/lowering/reduction/test_vector_norm.py::test_vector_norm[input_shape2-2-1] - AssertionError: 0.9045130848989367
Expected behavior PCC tests pass.
Please complete the following environment information:
The text was updated successfully, but these errors were encountered:
Mark known PCC issue with ttnn.moreh_norm (tenstorrent/tt-metal#16335)
67684b8
@mrshaw01 Would you assign our engineer for this issue?
Sorry, something went wrong.
@thd1007 let's take a look
@jdh8 what is your expected pcc? vector_norm implementation utilizes multiple operations with a fairly high impact on accuracy (namely exp and log).
vector_norm
@jdh8 can you please provide feedback to the prior comment? TY
thd1007
No branches or pull requests
Describe the bug
When
dim
is not the last dimension (-1), accuracy ofttnn.moreh_norm
drops.To Reproduce
Steps to reproduce the behavior:
aten.linalg_vector_norm
tottnn.moreh_norm
pytorch2.0_ttnn#686pytest tests/lowering/reduction/test_vector_norm.py --runxfail
Expected behavior
PCC tests pass.
Please complete the following environment information:
The text was updated successfully, but these errors were encountered: