Skip to content
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.

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

[TorchToLinalg]Implement lowering count_nonzero and count_nonzero.dim_IntList #3729

Open
wants to merge 4 commits into
base: main
Choose a base branch
from

Commits on Sep 24, 2024

  1. Implement lowering count_nonzero and count_nonzero.dim_IntList

    Use AtenNeScalaOp, AtenSumOp and AtenSumDimIntListOp to decompose
    Add 6 tests on different dtypes and for different shapes of input
    tensors
    Add verify to check correctness of input dim as int or list of ints
    um-urosmarkovic committed Sep 24, 2024
    Configuration menu
    Copy the full SHA
    592baf9 View commit details
    Browse the repository at this point in the history
  2. [TorchToLinalg]Implement lowering count_nonzero and `count_nonzero.…

    …dim_IntList`
    
    Use AtenNeScalaOp, AtenSumOp and AtenSumDimIntListOp to decompose
    Add 6 tests on different dtypes and for different shapes of input
    tensors
    Add verify to check correctness of input dim as int or list of ints
    Add tests to XFAIL on ONNX
    um-urosmarkovic committed Sep 24, 2024
    Configuration menu
    Copy the full SHA
    ab65e86 View commit details
    Browse the repository at this point in the history

Commits on Sep 25, 2024

  1. [TorchToLinalg]Implement lowering count_nonzero and `count_nonzero.…

    …dim_IntList`
    
    Use AtenNeScalaOp, AtenSumOp and AtenSumDimIntListOp to decompose
    Add 6 tests on different dtypes and for different shapes of input
    tensors
    Add verify to check correctness of input dim as int or list of ints
    Add tests to XFAIL on ONNX_FAIL set
    um-urosmarkovic committed Sep 25, 2024
    Configuration menu
    Copy the full SHA
    7687b9c View commit details
    Browse the repository at this point in the history
  2. [TorchToLinalg]Implement lowering count_nonzero and `count_nonzero.…

    …dim_IntList`
    
    Use AtenNeScalaOp, AtenSumOp and AtenSumDimIntListOp to decompose
    Add 6 tests on different dtypes and for different shapes of input
    tensors
    Add verify to check correctness of input dim as int or list of ints
    Add tests to XFAIL on ONNX_FAIL set
    Note: Torch upstream version < 2.5.0
    um-urosmarkovic committed Sep 25, 2024
    Configuration menu
    Copy the full SHA
    bc21335 View commit details
    Browse the repository at this point in the history