[IR] Support specifying output value in Tape

[justinchuby]

When a user wants to specify names for output values, they can initialize the value first then supply them to tape op() call.

Also renamed symbolic_multi_output to symblic_multi_out to match https://pytorch.org/docs/main/onnx_ops.html#torch.onnx.ops.symbolic_multi_out

[Copilot]

Pull Request Overview

This PR introduces support for specifying output values in Tape operations by allowing users to initialize and supply output values explicitly.

• Added an optional output parameter to op() to allow a single output value specification.
• Extended op_multi_output() with optional outputs in addition to num_outputs, with validation to ensure at least one is provided.

[codecov]

❌ 17 Tests Failed:

Tests completed	Failed	Passed	Skipped
14452	17	14435	1881

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

onnxscript.backend.onnx_export_test.TestOnnxBackEnd::test_export2python_produces_correct_onnx_script_model_1282_test_xor4d

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\3.10.11\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_xor4d'

The above exception was the direct cause of the following exception:
.nox\test\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_xor4d' (e=No module named 'tests.onnx_backend_test_code.test_xor4d') (file: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_xor4d.py', absolute path: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_xor4d.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
E   from onnxscript.onnx_opset import opset7
E   
E   @script()
E   def bck_test_xor4d(x: BOOL[3,4,5,6], y: BOOL[3,4,5,6]) -> (BOOL[3,4,5,6]):
E       xor = opset7.Xor(x, y)
E       return xor

onnxscript.backend.onnx_export_test.TestOnnxBackEnd::test_export2python_produces_correct_onnx_script_model_0125_test_bitwise_or_i32_2d

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\3.10.11\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_bitwise_or_i32_2d'

The above exception was the direct cause of the following exception:
.nox\test\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_bitwise_or_i32_2d' (e=No module named 'tests.onnx_backend_test_code.test_bitwise_or_i32_2d') (file: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_bitwise_or_i32_2d.py', absolute path: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_bitwise_or_i32_2d.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 INT32
E   from onnxscript.onnx_opset import opset18
E   
E   @script()
E   def bck_test_bitwise_or_i32_2d(x: INT32[3,4], y: INT32[3,4]) -> (INT32[3,4]):
E       bitwiseor = opset18.BitwiseOr(x, y)
E       return bitwiseor

onnxscript.backend.onnx_export_test.TestOnnxBackEnd::test_export2python_produces_correct_onnx_script_model_0139_test_castlike_DOUBLE_to_FLOAT16

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\3.10.11\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_castlike_DOUBLE_to_FLOAT16'

The above exception was the direct cause of the following exception:
.nox\test\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_castlike_DOUBLE_to_FLOAT16' (e=No module named 'tests.onnx_backend_test_code.test_castlike_DOUBLE_to_FLOAT16') (file: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_castlike_DOUBLE_to_FLOAT16.py', absolute path: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_castlike_DOUBLE_to_FLOAT16.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 DOUBLE, FLOAT16
E   from onnxscript.onnx_opset import opset21
E   
E   @script()
E   def bck_test_castlike_DOUBLE_to_FLOAT16(input: DOUBLE[3,4], like: FLOAT16[1]) -> (FLOAT16[3,4]):
E       output = opset21.CastLike(input, like)
E       return output

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

[gramalingam]

Are there any examples/documentation illustrating the creation of output value and then using it to create an op?

[justinchuby]

Are there any examples/documentation illustrating the creation of output value and then using it to create an op?

Will create as a follow up, thanks!