onnxscript 0.7.1.dev20260604__tar.gz → 0.7.1.dev20260609__tar.gz

{onnxscript-0.7.1.dev20260604/onnxscript.egg-info → onnxscript-0.7.1.dev20260609}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: onnxscript
-Version: 0.7.1.dev20260604
+Version: 0.7.1.dev20260609
 Summary: Naturally author ONNX functions and models using a subset of Python
 Author-email: Microsoft Corporation <onnx@microsoft.com>
 License: MIT License
@@ -27,7 +27,7 @@ License: MIT License
         
 Project-URL: Homepage, https://microsoft.github.io/onnxscript/
 Project-URL: Repository, https://github.com/microsoft/onnxscript
-Project-URL: Commit, https://github.com/microsoft/onnxscript/tree/e0d3edc6eb902a2dcc07e618b055234a2ef66665
+Project-URL: Commit, https://github.com/microsoft/onnxscript/tree/33d144535078fc06121d3cb17d32cb41f851afb0
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers

{onnxscript-0.7.1.dev20260604 → onnxscript-0.7.1.dev20260609}/onnxscript/function_libs/torch_lib/ops/core.py

@@ -4348,6 +4348,11 @@ def aten_gru(
         # Extract hidden_size from hx shape: [num_layers * num_directions, batch, hidden_size]
         hidden_size_attr = hx.shape[2]
 
+        # linear_before_reset=1 matches PyTorch's GRU formulation where the linear
+        # transformation is applied before multiplying by the reset gate:
+        #   ht = g(Xt*(Wh^T) + rt (.) (Ht-1*(Rh^T) + Rbh) + Wbh)
+        # The ONNX default (linear_before_reset=0) uses a different equation and
+        # would produce numerically incorrect results.
         if B is not None:
             Y, Y_h = op.GRU(
                 current_input,
@@ -4357,6 +4362,7 @@ def aten_gru(
                 initial_h=layer_h,
                 direction=direction,
                 hidden_size=hidden_size_attr,
+                linear_before_reset=1,
             )
         else:
             Y, Y_h = op.GRU(
@@ -4366,6 +4372,7 @@ def aten_gru(
                 initial_h=layer_h,
                 direction=direction,
                 hidden_size=hidden_size_attr,
+                linear_before_reset=1,
             )
 
         # Y shape: [seq_length, num_directions, batch_size, hidden_size]
@@ -6081,10 +6088,12 @@ def aten_masked_fill(self: TTensor, mask: BOOL, value: TTensor) -> TTensor:
 def aten_masked_scatter(self: TTensor, mask: TTensor, source: TTensor) -> TTensor:
     """masked_scatter(Tensor self, Tensor mask, Tensor source) -> Tensor"""
 
-    if len(mask.shape) < len(self.shape):
-        mask = op.Expand(mask, op.Shape(self))
-    else:
-        self = op.Expand(self, op.Shape(mask))
+    # Broadcast self and mask to their common shape so NonZero enumerates every
+    # masked element. The previous rank-only check missed same-rank broadcasting
+    # (e.g. mask (1, S, 1) vs self (1, S, D)): it left mask un-expanded, so only a
+    # subset of masked positions were scattered (pytorch/pytorch#186146).
+    self = op.Expand(self, op.Shape(mask))
+    mask = op.Expand(mask, op.Shape(self))
     index = op.Transpose(op.NonZero(mask), perm=[1, 0])
 
     # NOTE: source can have more elements than needed.

{onnxscript-0.7.1.dev20260604 → onnxscript-0.7.1.dev20260609/onnxscript.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: onnxscript
-Version: 0.7.1.dev20260604
+Version: 0.7.1.dev20260609
 Summary: Naturally author ONNX functions and models using a subset of Python
 Author-email: Microsoft Corporation <onnx@microsoft.com>
 License: MIT License
@@ -27,7 +27,7 @@ License: MIT License
         
 Project-URL: Homepage, https://microsoft.github.io/onnxscript/
 Project-URL: Repository, https://github.com/microsoft/onnxscript
-Project-URL: Commit, https://github.com/microsoft/onnxscript/tree/e0d3edc6eb902a2dcc07e618b055234a2ef66665
+Project-URL: Commit, https://github.com/microsoft/onnxscript/tree/33d144535078fc06121d3cb17d32cb41f851afb0
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers