Skip to content

Tags: onnx/ir-py

Tags

v0.1.5

Toggle v0.1.5's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Remove import from _custom_element_types in test (#136)

Remove import from _custom_element_types in test because the module is
removed in the latest version of onnx. I chose to remove the entries
instead of doing version checks because I don't expect the logic to be
broken for older onnx versions. When we bump the lowest supported onnx
version to be 1.19, we can remove the logic handling the custom types in
the from_numpy() method as well.

---------

Signed-off-by: Justin Chu <justinchuby@users.noreply.github.com>

v0.1.4

Toggle v0.1.4's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Fix 4bit tensor unpacking (#118)

4bit tensor unpacking to numpy array was buggy before this fix. I
updated the logic to make sure we correctly handle the bytes when
converting to numpy.

Added unit tests for all numeric dtypes.

---------

Signed-off-by: Justin Chu <justinchuby@users.noreply.github.com>

v0.1.3

Toggle v0.1.3's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Support numpy scalars in `Tensor` (#102)

Numpy scalars (https://numpy.org/doc/2.2/reference/arrays.scalars.html)
have `__array__` defined but doesn't behave like normal np arrays
sometimes. This change updates the initialization logic in `Tensor` to
detect them and turn them into np.ndarray.

Fixes #101.

---------

Signed-off-by: Justin Chu <justinchuby@users.noreply.github.com>

v0.1.2

Toggle v0.1.2's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Convenience function get_const_tensor (#45)

Get the constant tensor from a value, if it exists.

A constant tensor can be obtained if the value has a ``const_value`` set
(as in the case of an initializer) or if the value is produced by a
Constant node.

This function will not alter the ``const_value`` of the value, but
it will propagate the shape and type of the constant tensor to the value
if `propagate_shape_type` is set to True.

---------

Signed-off-by: Justin Chu <justinchuby@users.noreply.github.com>
Co-authored-by: codecov-ai[bot] <156709835+codecov-ai[bot]@users.noreply.github.com>

v0.1.1

Toggle v0.1.1's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
[pass] Add CSE (#36)

CSE pass from microsoft/onnxscript#2304

---------

Signed-off-by: Ti-Tai Wang <titaiwang@microsoft.com>
Signed-off-by: Justin Chu <justinchuby@users.noreply.github.com>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Justin Chu <justinchuby@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

v0.1.0

Toggle v0.1.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Implement `is_floating_point` on dtypes (#31)

Migration of changes in
microsoft/onnxscript#2335

Signed-off-by: Justin Chu <justinchuby@users.noreply.github.com>