Enable extraction of rewritten subgraph as model-local function

[gramalingam]

Enable extraction of rewritten subgraph as model-local function.

This will enable multi-step rewrite optimizations: eg., map subgraph G1 to new-op1, and then map subgraph G2 containing new-op1 to new-op2, and then inlining can replace any remaining new-op1 (that was not rewritten) by original G1.

[codecov]

❌ 24 Tests Failed:

Tests completed	Failed	Passed	Skipped
10987	24	10963	1865

View the top 3 failed test(s) by shortest run time

onnxscript.backend.onnx_export_test.TestOnnxBackEnd::test_export2python_produces_correct_onnx_script_model_0266_test_compress_1

Stack Traces | 0.003s run time

onnxscript\backend\onnx_export_test.py:137: in extract_functions
    mod = importlib.import_module(import_name)
C:\hostedtoolcache\windows\Python\3.11.9\x64\Lib\importlib\__init__.py:126: in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
E   ModuleNotFoundError: No module named 'tests.onnx_backend_test_code.test_compress_1'

The above exception was the direct cause of the following exception:
.nox\test_onnx_weekly\Lib\site-packages\parameterized\parameterized.py:620: in standalone_func
    return func(*(a + p.args), **p.kwargs, **kw)
onnxscript\backend\onnx_export_test.py:271: in test_export2python_produces_correct_onnx_script_model
    functions = extract_functions(backend_test.name, code, self.test_folder)
onnxscript\backend\onnx_export_test.py:139: in extract_functions
    raise AssertionError(
E   AssertionError: Unable to import 'tests.onnx_backend_test_code.test_compress_1' (e=No module named 'tests.onnx_backend_test_code.test_compress_1') (file: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_compress_1.py', absolute path: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_compress_1.py', current folder: D:\a\onnxscript\onnxscript
E   ---- CONTENT --
E   import numpy
E   from onnx import TensorProto
E   from onnx.helper import make_tensor
E   from onnxscript import script, external_tensor
E   from onnxscript.values import Opset
E   from onnxscript.onnx_types import BOOL, FLOAT
E   from onnxscript.onnx_opset import opset11
E   
E   @script()
E   def bck_test_compress_1(input: FLOAT[3,2], condition: BOOL[2]) -> (FLOAT[3,1]):
E       output = opset11.Compress(input, condition, axis=1)
E       return output

onnxscript.backend.onnx_export_test.TestOnnxBackEnd::test_export2python_produces_correct_onnx_script_model_0340_test_div

Stack Traces | 0.004s run time

onnxscript\backend\onnx_export_test.py:137: in extract_functions
    mod = importlib.import_module(import_name)
C:\hostedtoolcache\windows\Python\3.11.9\x64\Lib\importlib\__init__.py:126: in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
E   ModuleNotFoundError: No module named 'tests.onnx_backend_test_code.test_div'

The above exception was the direct cause of the following exception:
.nox\test_onnx_weekly\Lib\site-packages\parameterized\parameterized.py:620: in standalone_func
    return func(*(a + p.args), **p.kwargs, **kw)
onnxscript\backend\onnx_export_test.py:271: in test_export2python_produces_correct_onnx_script_model
    functions = extract_functions(backend_test.name, code, self.test_folder)
onnxscript\backend\onnx_export_test.py:139: in extract_functions
    raise AssertionError(
E   AssertionError: Unable to import 'tests.onnx_backend_test_code.test_div' (e=No module named 'tests.onnx_backend_test_code.test_div') (file: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_div.py', absolute path: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_div.py', current folder: D:\a\onnxscript\onnxscript
E   ---- CONTENT --
E   import numpy
E   from onnx import TensorProto
E   from onnx.helper import make_tensor
E   from onnxscript import script, external_tensor
E   from onnxscript.values import Opset
E   from onnxscript.onnx_types import FLOAT
E   from onnxscript.onnx_opset import opset14
E   
E   @script()
E   def bck_test_div(x: FLOAT[3,4,5], y: FLOAT[3,4,5]) -> (FLOAT[3,4,5]):
E       z = opset14.Div(x, y)
E       return z

onnxscript.backend.onnx_export_test.TestOnnxBackEnd::test_export2python_produces_correct_onnx_script_model_0911_test_reduce_sum_default_axes_keepdims_random

Stack Traces | 0.004s run time

onnxscript\backend\onnx_export_test.py:137: in extract_functions
    mod = importlib.import_module(import_name)
C:\hostedtoolcache\windows\Python\3.11.9\x64\Lib\importlib\__init__.py:126: in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
E   ModuleNotFoundError: No module named 'tests.onnx_backend_test_code.test_reduce_sum_default_axes_keepdims_random'

The above exception was the direct cause of the following exception:
.nox\test_torch_nightly\Lib\site-packages\parameterized\parameterized.py:620: in standalone_func
    return func(*(a + p.args), **p.kwargs, **kw)
onnxscript\backend\onnx_export_test.py:271: in test_export2python_produces_correct_onnx_script_model
    functions = extract_functions(backend_test.name, code, self.test_folder)
onnxscript\backend\onnx_export_test.py:139: in extract_functions
    raise AssertionError(
E   AssertionError: Unable to import 'tests.onnx_backend_test_code.test_reduce_sum_default_axes_keepdims_random' (e=No module named 'tests.onnx_backend_test_code.test_reduce_sum_default_axes_keepdims_random') (file: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_reduce_sum_default_axes_keepdims_random.py', absolute path: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_reduce_sum_default_axes_keepdims_random.py', current folder: D:\a\onnxscript\onnxscript
E   ---- CONTENT --
E   import numpy
E   from onnx import TensorProto
E   from onnx.helper import make_tensor
E   from onnxscript import script, external_tensor
E   from onnxscript.values import Opset
E   from onnxscript.onnx_types import FLOAT, INT64
E   from onnxscript.onnx_opset import opset13
E   
E   @script()
E   def bck_test_reduce_sum_default_axes_keepdims_random(data: FLOAT[3,2,2], axes: INT64[0]) -> (FLOAT[1,1,1]):
E       reduced = opset13.ReduceSum(data, axes, keepdims=1)
E       return reduced

To view more test analytics, go to the Test Analytics Dashboard
_{📋 Got 3 mins? Take this short survey to help us improve Test Analytics.}

Copilot reviewed 3 out of 3 changed files in this pull request and generated no comments.

Comments suppressed due to low confidence (2)

onnxscript/rewriter/pattern_test.py:583

• [nitpick] The variable name 'sum' shadows the built-in function 'sum'. Consider renaming it (e.g., to 'result' or 'total') to avoid confusion.

            sum = op.Add(x, y)

onnxscript/rewriter/pattern.py:1541

• [nitpick] Using 'input' as a loop variable shadows the built-in function 'input'. Renaming it (for example, to 'inp') would improve code clarity.

    for input in inputs: