onnx-ir 0.1.7__tar.gz → 0.1.8__tar.gz

{onnx_ir-0.1.7/src/onnx_ir.egg-info → onnx_ir-0.1.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: onnx-ir
-Version: 0.1.7
+Version: 0.1.8
 Summary: Efficient in-memory representation for ONNX
 Author-email: ONNX Contributors <onnx-technical-discuss@lists.lfaidata.foundation>
 License-Expression: Apache-2.0
@@ -22,7 +22,7 @@ Requires-Dist: typing_extensions>=4.10
 Requires-Dist: ml_dtypes
 Dynamic: license-file
 
-# ONNX IR
+# <img src="docs/_static/logo-light.png" alt="ONNX IR" width="250"/>
 
 [![PyPI - Version](https://img.shields.io/pypi/v/onnx-ir.svg)](https://pypi.org/project/onnx-ir)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/onnx-ir.svg)](https://pypi.org/project/onnx-ir)
@@ -60,6 +60,10 @@ pip install git+https://github.com/onnx/ir-py.git
 - Pythonic and familiar APIs: Classes define Pythonic apis and still map to ONNX protobuf concepts in an intuitive way.
 - No protobuf dependency: The IR does not require protobuf once the model is converted to the IR representation, decoupling from the serialization format.
 
+## Concept Diagram
+
+![Concept Diagram](docs/resource/onnx-ir-entities.svg)
+
 ## Code Organization 🗺️
 
 - [`_protocols.py`](src/onnx_ir/_protocols.py): Interfaces defined for all entities in the IR.

{onnx_ir-0.1.7 → onnx_ir-0.1.8}/README.md

@@ -1,4 +1,4 @@
-# ONNX IR
+# <img src="docs/_static/logo-light.png" alt="ONNX IR" width="250"/>
 
 [![PyPI - Version](https://img.shields.io/pypi/v/onnx-ir.svg)](https://pypi.org/project/onnx-ir)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/onnx-ir.svg)](https://pypi.org/project/onnx-ir)
@@ -36,6 +36,10 @@ pip install git+https://github.com/onnx/ir-py.git
 - Pythonic and familiar APIs: Classes define Pythonic apis and still map to ONNX protobuf concepts in an intuitive way.
 - No protobuf dependency: The IR does not require protobuf once the model is converted to the IR representation, decoupling from the serialization format.
 
+## Concept Diagram
+
+![Concept Diagram](docs/resource/onnx-ir-entities.svg)
+
 ## Code Organization 🗺️
 
 - [`_protocols.py`](src/onnx_ir/_protocols.py): Interfaces defined for all entities in the IR.

{onnx_ir-0.1.7 → onnx_ir-0.1.8}/src/onnx_ir/__init__.py

@@ -167,4 +167,4 @@ def __set_module() -> None:
 
 
 __set_module()
-__version__ = "0.1.7"
+__version__ = "0.1.8"

{onnx_ir-0.1.7 → onnx_ir-0.1.8}/src/onnx_ir/_core.py

@@ -836,6 +836,11 @@ class StringTensor(TensorBase, _protocols.TensorProtocol):  # pylint: disable=to
         """The shape of the tensor. Immutable."""
         return self._shape
 
+    @property
+    def nbytes(self) -> int:
+        """The number of bytes in the tensor."""
+        return sum(len(string) for string in self.string_data())
+
     @property
     def raw(self) -> Sequence[bytes] | npt.NDArray[np.bytes_]:
         """Backing data of the tensor. Immutable."""

{onnx_ir-0.1.7 → onnx_ir-0.1.8}/src/onnx_ir/_enums.py

@@ -5,6 +5,7 @@
 from __future__ import annotations
 
 import enum
+from typing import Any
 
 import ml_dtypes
 import numpy as np
@@ -77,7 +78,7 @@ class DataType(enum.IntEnum):
         if dtype in _NP_TYPE_TO_DATA_TYPE:
             return cls(_NP_TYPE_TO_DATA_TYPE[dtype])
 
-        if np.issubdtype(dtype, np.str_):
+        if np.issubdtype(dtype, np.str_) or np.issubdtype(dtype, np.bytes_):
             return DataType.STRING
 
         # Special cases for handling custom dtypes defined in ONNX (as of onnx 1.18)
@@ -131,6 +132,146 @@ class DataType(enum.IntEnum):
             raise TypeError(f"Bitwidth not available for ONNX data type: {self}")
         return _BITWIDTH_MAP[self]
 
+    @property
+    def exponent_bitwidth(self) -> int:
+        """Returns the bit width of the exponent for floating-point types.
+
+        .. versionadded:: 0.1.8
+
+        Raises:
+            TypeError: If the data type is not supported.
+        """
+        if self.is_floating_point():
+            return ml_dtypes.finfo(self.numpy()).nexp
+
+        raise TypeError(f"Exponent not available for ONNX data type: {self}")
+
+    @property
+    def mantissa_bitwidth(self) -> int:
+        """Returns the bit width of the mantissa for floating-point types.
+
+        .. versionadded:: 0.1.8
+
+        Raises:
+            TypeError: If the data type is not supported.
+        """
+        if self.is_floating_point():
+            return ml_dtypes.finfo(self.numpy()).nmant
+
+        raise TypeError(f"Mantissa not available for ONNX data type: {self}")
+
+    @property
+    def eps(self) -> int | np.floating[Any]:
+        """Returns the difference between 1.0 and the next smallest representable float larger than 1.0 for the ONNX data type.
+
+        Returns 1 for integers.
+
+        .. versionadded:: 0.1.8
+
+        Raises:
+            TypeError: If the data type is not a numeric data type.
+        """
+        if self.is_integer():
+            return 1
+
+        if self.is_floating_point():
+            return ml_dtypes.finfo(self.numpy()).eps
+
+        raise TypeError(f"Eps not available for ONNX data type: {self}")
+
+    @property
+    def tiny(self) -> int | np.floating[Any]:
+        """Returns the smallest positive non-zero value for the ONNX data type.
+
+        Returns 1 for integers.
+
+        .. versionadded:: 0.1.8
+
+        Raises:
+            TypeError: If the data type is not a numeric data type.
+        """
+        if self.is_integer():
+            return 1
+
+        if self.is_floating_point():
+            return ml_dtypes.finfo(self.numpy()).tiny
+
+        raise TypeError(f"Tiny not available for ONNX data type: {self}")
+
+    @property
+    def min(self) -> int | np.floating[Any]:
+        """Returns the minimum representable value for the ONNX data type.
+
+        .. versionadded:: 0.1.8
+
+        Raises:
+            TypeError: If the data type is not a numeric data type.
+        """
+        if self.is_integer():
+            return ml_dtypes.iinfo(self.numpy()).min
+
+        if self.is_floating_point():
+            return ml_dtypes.finfo(self.numpy()).min
+
+        raise TypeError(f"Minimum not available for ONNX data type: {self}")
+
+    @property
+    def max(self) -> int | np.floating[Any]:
+        """Returns the maximum representable value for the ONNX data type.
+
+        .. versionadded:: 0.1.8
+
+        Raises:
+            TypeError: If the data type is not a numeric data type.
+        """
+        if self.is_integer():
+            return ml_dtypes.iinfo(self.numpy()).max
+
+        if self.is_floating_point():
+            return ml_dtypes.finfo(self.numpy()).max
+
+        raise TypeError(f"Maximum not available for ONNX data type: {self}")
+
+    @property
+    def precision(self) -> int:
+        """Returns the precision for the ONNX dtype if supported.
+
+        For floats returns the approximate number of decimal digits to which
+        this kind of float is precise. Returns 0 for integers.
+
+        .. versionadded:: 0.1.8
+
+        Raises:
+            TypeError: If the data type is not a numeric data type.
+        """
+        if self.is_integer():
+            return 0
+
+        if self.is_floating_point():
+            return ml_dtypes.finfo(self.numpy()).precision
+
+        raise TypeError(f"Precision not available for ONNX data type: {self}")
+
+    @property
+    def resolution(self) -> int | np.floating[Any]:
+        """Returns the resolution for the ONNX dtype if supported.
+
+        Returns the approximate decimal resolution of this type, i.e.,
+         10**-precision. Returns 1 for integers.
+
+        .. versionadded:: 0.1.8
+
+        Raises:
+            TypeError: If the data type is not a numeric data type.
+        """
+        if self.is_integer():
+            return 1
+
+        if self.is_floating_point():
+            return ml_dtypes.finfo(self.numpy()).resolution
+
+        raise TypeError(f"Resolution not available for ONNX data type: {self}")
+
     def numpy(self) -> np.dtype:
         """Returns the numpy dtype for the ONNX data type.
 
@@ -215,6 +356,10 @@ class DataType(enum.IntEnum):
             DataType.FLOAT8E8M0,
         }
 
+    def is_string(self) -> bool:
+        """Returns True if the data type is a string type."""
+        return self == DataType.STRING
+
     def __repr__(self) -> str:
         return self.name
 

{onnx_ir-0.1.7 → onnx_ir-0.1.8}/src/onnx_ir/passes/common/initializer_deduplication.py

@@ -10,6 +10,8 @@ __all__ = ["DeduplicateInitializersPass", "DeduplicateHashedInitializersPass"]
 import hashlib
 import logging
 
+import numpy as np
+
 import onnx_ir as ir
 
 logger = logging.getLogger(__name__)
@@ -42,17 +44,27 @@ def _should_skip_initializer(initializer: ir.Value, size_limit: int) -> bool:
             size_limit,
         )
         return True
-
-    if const_val.dtype == ir.DataType.STRING:
-        # Skip string initializers as they don't have a bytes representation
-        logger.warning(
-            "Skipped deduplication of string initializer '%s' (unsupported yet)",
-            initializer.name,
-        )
-        return True
     return False
 
 
+def _tobytes(val):
+    """StringTensor does not support tobytes. Use 'string_data' instead.
+
+    However, 'string_data' yields a list of bytes which cannot be hashed, i.e.,
+    cannot be used to index into a dict. To generate keys for identifying
+    tensors in initializer deduplication the following converts the list of
+    bytes to an array of fixed-length strings which can be flattened into a
+    bytes-string. This, together with the tensor shape, is sufficient for
+    identifying tensors for deduplication, but it differs from the
+    representation used for serializing tensors (that is string_data) by adding
+    padding bytes so that each string occupies the same number of consecutive
+    bytes in the flattened .tobytes representation.
+    """
+    if val.dtype.is_string():
+        return np.array(val.string_data()).tobytes()
+    return val.tobytes()
+
+
 class DeduplicateInitializersPass(ir.passes.InPlacePass):
     """Remove duplicated initializer tensors from the main graph and all subgraphs.
 
@@ -84,7 +96,7 @@ class DeduplicateInitializersPass(ir.passes.InPlacePass):
                 const_val = initializer.const_value
                 assert const_val is not None
 
-                key = (const_val.dtype, tuple(const_val.shape), const_val.tobytes())
+                key = (const_val.dtype, tuple(const_val.shape), _tobytes(const_val))
                 if key in initializers:
                     modified = True
                     initializer_to_keep = initializers[key]  # type: ignore[index]
@@ -143,7 +155,7 @@ class DeduplicateHashedInitializersPass(ir.passes.InPlacePass):
                 key = (const_val.dtype, tensor_dims, tensor_digest)
 
                 if key in initializers:
-                    if initializers[key].const_value.tobytes() != const_val.tobytes():
+                    if _tobytes(initializers[key].const_value) != _tobytes(const_val):
                         logger.warning(
                             "Initializer deduplication failed: "
                             "hashes match but values differ with values %s and %s",

{onnx_ir-0.1.7 → onnx_ir-0.1.8}/src/onnx_ir/serde.py

@@ -1784,11 +1784,12 @@ def _fill_in_value_for_attribute(
 ) -> None:
     if type_ == _enums.AttributeType.INT:
         # value: int
-        attribute_proto.i = value
+        # Cast bool to int, for example
+        attribute_proto.i = int(value)
         attribute_proto.type = onnx.AttributeProto.INT
     elif type_ == _enums.AttributeType.FLOAT:
         # value: float
-        attribute_proto.f = value
+        attribute_proto.f = float(value)
         attribute_proto.type = onnx.AttributeProto.FLOAT
     elif type_ == _enums.AttributeType.STRING:
         # value: str

{onnx_ir-0.1.7 → onnx_ir-0.1.8/src/onnx_ir.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: onnx-ir
-Version: 0.1.7
+Version: 0.1.8
 Summary: Efficient in-memory representation for ONNX
 Author-email: ONNX Contributors <onnx-technical-discuss@lists.lfaidata.foundation>
 License-Expression: Apache-2.0
@@ -22,7 +22,7 @@ Requires-Dist: typing_extensions>=4.10
 Requires-Dist: ml_dtypes
 Dynamic: license-file
 
-# ONNX IR
+# <img src="docs/_static/logo-light.png" alt="ONNX IR" width="250"/>
 
 [![PyPI - Version](https://img.shields.io/pypi/v/onnx-ir.svg)](https://pypi.org/project/onnx-ir)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/onnx-ir.svg)](https://pypi.org/project/onnx-ir)
@@ -60,6 +60,10 @@ pip install git+https://github.com/onnx/ir-py.git
 - Pythonic and familiar APIs: Classes define Pythonic apis and still map to ONNX protobuf concepts in an intuitive way.
 - No protobuf dependency: The IR does not require protobuf once the model is converted to the IR representation, decoupling from the serialization format.
 
+## Concept Diagram
+
+![Concept Diagram](docs/resource/onnx-ir-entities.svg)
+
 ## Code Organization 🗺️
 
 - [`_protocols.py`](src/onnx_ir/_protocols.py): Interfaces defined for all entities in the IR.