[pass] Create version converter pass #2214

justinchuby · 2025-04-19T01:57:57Z

Use both the onnxscript version converter and optionally fall back to the onnx version converter if the target version is unsupported.

Created version_supported helper function for users to check if a target version is supported by the onnxscript version converter.

Use the converter in pytorch apis.

Copilot

Pull Request Overview

This PR adds a version conversion pass that uses the onnxscript version converter with an option to fall back to the onnx C API converter when necessary.

Renamed constant CURRENT_MAX_ONNX_OPSET to SUPPORTED_MAX_ONNX_OPSET and added SUPPORTED_MIN_ONNX_OPSET.
Introduced a new function version_supported and modified the ConvertVersionPass to incorporate a fallback mechanism.
Updated the convert_version API to accept a fallback parameter.

Reviewed Changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.

File	Description
onnxscript/version_converter/_version_converter.py	Updated op set constants, added version_supported function with a potentially incorrect inequality chain.
onnxscript/version_converter/init.py	Modified convert_version API to include a fallback parameter with an inconsistent default value compared to its docstring.
onnxscript/ir/passes/common/version_converter.py	Added ConvertVersionPass that leverages the updated version converter and fallback mechanism.

onnxscript/version_converter/_version_converter.py

onnxscript/version_converter/__init__.py

Co-authored-by: Copilot <[email protected]>

onnxscript/version_converter/_version_converter.py

codecov · 2025-04-19T02:04:34Z

❌ 3 Tests Failed:

Tests completed	Failed	Passed	Skipped
16051	3	16048	1698

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

onnxscript.backend.onnx_export_test.TestOnnxBackEnd::test_export2python_produces_correct_onnx_script_model_0397_test_ai_onnx_ml_tree_ensemble_set_membership

Stack Traces | 0.011s run time

onnxscript/converter.py:460: in _eval_constant_expr
    return eval(cpl, self.globals, locals)  # pylint: disable=eval-used
E   NameError: name 'nan' is not defined

The above exception was the direct cause of the following exception:
..../test_ort_nightly/lib/python3.11.../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:137: in extract_functions
    mod = importlib.import_module(import_name)
.../hostedtoolcache/Python/3.11.12.../x64/lib/python3.11/importlib/__init__.py:126: in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
<frozen importlib._bootstrap>:1204: in _gcd_import
    ???
<frozen importlib._bootstrap>:1176: in _find_and_load
    ???
<frozen importlib._bootstrap>:1147: in _find_and_load_unlocked
    ???
<frozen importlib._bootstrap>:690: in _load_unlocked
    ???
..../test_ort_nightly/lib/python3.11.../_pytest/assertion/rewrite.py:185: in exec_module
    exec(co, module.__dict__)
tests/onnx_backend_test_code/test_ai_onnx_ml_tree_ensemble_set_membership.py:9: in <module>
    @script()
onnxscript/main.py:95: in transform
    result = script_check(f_ast, opset, env, src, default_opset=default_opset)
onnxscript/main.py:39: in script_check
    return convert.translate_function_def(f)
onnxscript/converter.py:1452: in translate_function_def
    fn_ir = self._translate_function_def_common(stmt)
onnxscript/converter.py:1439: in _translate_function_def_common
    self._translate_stmt(s, index_of_stmt=i)
onnxscript/converter.py:961: in _translate_stmt
    return self._translate_assign_stmt(node)
onnxscript/converter.py:1048: in _translate_assign_stmt
    assign(lhs, rhs)
onnxscript/converter.py:992: in assign
    t = self._translate_expr(rhs, lhs).name
onnxscript/converter.py:546: in _translate_expr
    r = self._translate_call_expr(node)
onnxscript/converter.py:825: in _translate_call_expr
    attrs = [
onnxscript/converter.py:826: in <listcomp>
    self._translate_attr(x, y, callee.op_schema.attributes[x])
onnxscript/converter.py:510: in _translate_attr
    val = self._eval_constant_expr(expr)
onnxscript/converter.py:462: in _eval_constant_expr
    raise NameError(
E   NameError: ERROR: Missing names, globals contains ['__name__', '__doc__', '__package__', '__loader__', '__spec__', '__file__', '__cached__', '__builtins__', '@py_builtins', '@pytest_ar', 'numpy', 'TensorProto', 'make_tensor', 'script', 'external_tensor', 'Opset', 'FLOAT', 'ai_onnx_ml5'], locals [].
E   at: Function 'bck_test_ai_onnx_ml_tree_ensemble_set_membership', line 3
E       Y = ai_onnx_ml5.TreeEnsemble(X, aggregate_function=1, leaf_targetids=[0, 1, 2, 3], leaf_weights=make_tensor("value", 1, dims=[4], vals=[1.0, 10.0, 1000.0, 100.0]), membership_values=make_tensor("value", 1, dims=[8], vals=[1.2000000476837158, 3.700000047683716, 8.0, 9.0, nan, 12.0, 7.0, nan]), n_targets=4, nodes_falseleafs=[1, 0, 1], nodes_falsenodeids=[2, 2, 3], nodes_featureids=[0, 0, 0], nodes_modes=make_tensor("value", 2, dims=[3], vals=[0, 6, 6]), nodes_splits=make_tensor("value", 1, dims=[3], vals=[11.0, 232344.0, nan]), nodes_trueleafs=[0, 1, 1], nodes_truenodeids=[1, 0, 1], post_transform=0, tree_roots=[0])
E                                                                                                                                                                                             ^

onnxscript.backend.onnx_export_test.TestOnnxBackEnd::test_export2python_produces_correct_onnx_script_model_0026_test_ai_onnx_ml_tree_ensemble_set_membership

Stack Traces | 0.03s run time

onnxscript\converter.py:460: in _eval_constant_expr
    return eval(cpl, self.globals, locals)  # pylint: disable=eval-used
E   NameError: name 'nan' is not defined

The above exception was the direct cause of the following exception:
.nox\test_ort_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: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)
<frozen importlib._bootstrap>:1204: in _gcd_import
    ???
<frozen importlib._bootstrap>:1176: in _find_and_load
    ???
<frozen importlib._bootstrap>:1147: in _find_and_load_unlocked
    ???
<frozen importlib._bootstrap>:690: in _load_unlocked
    ???
.nox\test_ort_nightly\Lib\site-packages\_pytest\assertion\rewrite.py:185: in exec_module
    exec(co, module.__dict__)
tests\onnx_backend_test_code\test_ai_onnx_ml_tree_ensemble_set_membership.py:9: in <module>
    @script()
onnxscript\main.py:95: in transform
    result = script_check(f_ast, opset, env, src, default_opset=default_opset)
onnxscript\main.py:39: in script_check
    return convert.translate_function_def(f)
onnxscript\converter.py:1452: in translate_function_def
    fn_ir = self._translate_function_def_common(stmt)
onnxscript\converter.py:1439: in _translate_function_def_common
    self._translate_stmt(s, index_of_stmt=i)
onnxscript\converter.py:961: in _translate_stmt
    return self._translate_assign_stmt(node)
onnxscript\converter.py:1048: in _translate_assign_stmt
    assign(lhs, rhs)
onnxscript\converter.py:992: in assign
    t = self._translate_expr(rhs, lhs).name
onnxscript\converter.py:546: in _translate_expr
    r = self._translate_call_expr(node)
onnxscript\converter.py:825: in _translate_call_expr
    attrs = [
onnxscript\converter.py:826: in <listcomp>
    self._translate_attr(x, y, callee.op_schema.attributes[x])
onnxscript\converter.py:510: in _translate_attr
    val = self._eval_constant_expr(expr)
onnxscript\converter.py:462: in _eval_constant_expr
    raise NameError(
E   NameError: ERROR: Missing names, globals contains ['__name__', '__doc__', '__package__', '__loader__', '__spec__', '__file__', '__cached__', '__builtins__', '@py_builtins', '@pytest_ar', 'numpy', 'TensorProto', 'make_tensor', 'script', 'external_tensor', 'Opset', 'FLOAT', 'ai_onnx_ml5'], locals [].
E   at: Function 'bck_test_ai_onnx_ml_tree_ensemble_set_membership', line 3
E       Y = ai_onnx_ml5.TreeEnsemble(X, aggregate_function=1, leaf_targetids=[0, 1, 2, 3], leaf_weights=make_tensor("value", 1, dims=[4], vals=[1.0, 10.0, 1000.0, 100.0]), membership_values=make_tensor("value", 1, dims=[8], vals=[1.2000000476837158, 3.700000047683716, 8.0, 9.0, nan, 12.0, 7.0, nan]), n_targets=4, nodes_falseleafs=[1, 0, 1], nodes_falsenodeids=[2, 2, 3], nodes_featureids=[0, 0, 0], nodes_modes=make_tensor("value", 2, dims=[3], vals=[0, 6, 6]), nodes_splits=make_tensor("value", 1, dims=[3], vals=[11.0, 232344.0, nan]), nodes_trueleafs=[0, 1, 1], nodes_truenodeids=[1, 0, 1], post_transform=0, tree_roots=[0])
E                                                                                                                                                                                             ^

onnxscript.backend.onnx_export_test.TestOnnxBackEnd::test_export2python_produces_correct_onnx_script_model_0125_test_ai_onnx_ml_tree_ensemble_set_membership

Stack Traces | 0.056s run time

onnxscript/converter.py:460: in _eval_constant_expr
    return eval(cpl, self.globals, locals)  # pylint: disable=eval-used
E   NameError: name 'nan' is not defined

The above exception was the direct cause of the following exception:
..../test_ort_nightly/lib/python3.11.../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:137: in extract_functions
    mod = importlib.import_module(import_name)
.../Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/importlib/__init__.py:126: in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
<frozen importlib._bootstrap>:1204: in _gcd_import
    ???
<frozen importlib._bootstrap>:1176: in _find_and_load
    ???
<frozen importlib._bootstrap>:1147: in _find_and_load_unlocked
    ???
<frozen importlib._bootstrap>:690: in _load_unlocked
    ???
..../test_ort_nightly/lib/python3.11.../_pytest/assertion/rewrite.py:185: in exec_module
    exec(co, module.__dict__)
tests/onnx_backend_test_code/test_ai_onnx_ml_tree_ensemble_set_membership.py:9: in <module>
    @script()
onnxscript/main.py:95: in transform
    result = script_check(f_ast, opset, env, src, default_opset=default_opset)
onnxscript/main.py:39: in script_check
    return convert.translate_function_def(f)
onnxscript/converter.py:1452: in translate_function_def
    fn_ir = self._translate_function_def_common(stmt)
onnxscript/converter.py:1439: in _translate_function_def_common
    self._translate_stmt(s, index_of_stmt=i)
onnxscript/converter.py:961: in _translate_stmt
    return self._translate_assign_stmt(node)
onnxscript/converter.py:1048: in _translate_assign_stmt
    assign(lhs, rhs)
onnxscript/converter.py:992: in assign
    t = self._translate_expr(rhs, lhs).name
onnxscript/converter.py:546: in _translate_expr
    r = self._translate_call_expr(node)
onnxscript/converter.py:825: in _translate_call_expr
    attrs = [
onnxscript/converter.py:826: in <listcomp>
    self._translate_attr(x, y, callee.op_schema.attributes[x])
onnxscript/converter.py:510: in _translate_attr
    val = self._eval_constant_expr(expr)
onnxscript/converter.py:462: in _eval_constant_expr
    raise NameError(
E   NameError: ERROR: Missing names, globals contains ['__name__', '__doc__', '__package__', '__loader__', '__spec__', '__file__', '__cached__', '__builtins__', '@py_builtins', '@pytest_ar', 'numpy', 'TensorProto', 'make_tensor', 'script', 'external_tensor', 'Opset', 'FLOAT', 'ai_onnx_ml5'], locals [].
E   at: Function 'bck_test_ai_onnx_ml_tree_ensemble_set_membership', line 3
E       Y = ai_onnx_ml5.TreeEnsemble(X, aggregate_function=1, leaf_targetids=[0, 1, 2, 3], leaf_weights=make_tensor("value", 1, dims=[4], vals=[1.0, 10.0, 1000.0, 100.0]), membership_values=make_tensor("value", 1, dims=[8], vals=[1.2000000476837158, 3.700000047683716, 8.0, 9.0, nan, 12.0, 7.0, nan]), n_targets=4, nodes_falseleafs=[1, 0, 1], nodes_falsenodeids=[2, 2, 3], nodes_featureids=[0, 0, 0], nodes_modes=make_tensor("value", 2, dims=[3], vals=[0, 6, 6]), nodes_splits=make_tensor("value", 1, dims=[3], vals=[11.0, 232344.0, nan]), nodes_trueleafs=[0, 1, 1], nodes_truenodeids=[1, 0, 1], post_transform=0, tree_roots=[0])
E                                                                                                                                                                                             ^

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

onnxscript/ir/passes/common/version_converter.py

onnxscript/version_converter/__init__.py

Co-authored-by: Shubham Bhokare <[email protected]>

onnxscript/version_converter/__init__.py

Copilot

Pull Request Overview

This PR introduces a new version conversion pass that utilizes the onnxscript version converter with an optional fallback to the ONNX C API when a target version is unsupported. Key changes include test coverage for version conversion, updates to the version converter implementation (including renaming constants and adding a version_supported helper), and integration of the new pass into the PyTorch API conversion flow.

Reviewed Changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
tests/version_converter/version_conversion_test.py	Added tests ensuring the conversion behavior when fallback is enabled.
onnxscript/version_converter/_version_converter_test.py	Fixed a typo in the test class name from "ApapterCoverageTest" to "AdapterCoverageTest".
onnxscript/version_converter/_version_converter.py	Updated constants and implemented the version_supported helper; improved warning logic.
onnxscript/version_converter/init.py	Introduced the ConvertVersionPass and updated the convert_version function signature.
onnxscript/_framework_apis/torch_2_6.py	Modified the conversion flow to use the new pass, with a warning for unsupported opset < 18.

Comments suppressed due to low confidence (1)

onnxscript/version_converter/_version_converter.py:137

[nitpick] Consider renaming the loop variable 'input' to avoid shadowing the built-in function 'input'.

for input in converted_model.graph.inputs:

justinchuby added 2 commits April 18, 2025 18:56

[pass] Create version converter pass

067b361

format

e62f787

justinchuby requested review from shubhambhokare1 and Copilot April 19, 2025 01:57

github-project-automation bot added this to ONNX Script Review Board Apr 19, 2025

github-project-automation bot moved this to Todo in ONNX Script Review Board Apr 19, 2025

Copilot AI reviewed Apr 19, 2025

View reviewed changes

onnxscript/version_converter/_version_converter.py Outdated Show resolved Hide resolved

onnxscript/version_converter/__init__.py Show resolved Hide resolved

justinchuby and others added 2 commits April 18, 2025 18:59

Update onnxscript/version_converter/_version_converter.py

0a29775

Co-authored-by: Copilot <[email protected]>

doc

f3c1638

justinchuby requested a review from titaiwangms April 19, 2025 02:00

justinchuby commented Apr 19, 2025

View reviewed changes

onnxscript/version_converter/_version_converter.py Show resolved Hide resolved

Update onnxscript/version_converter/_version_converter.py

9d6b1c8

justinchuby added the topic: passes label Apr 19, 2025

github-advanced-security bot found potential problems Apr 19, 2025

View reviewed changes

onnxscript/ir/passes/common/version_converter.py Fixed Show fixed Hide fixed

onnxscript/ir/passes/common/version_converter.py Fixed Show fixed Hide fixed

justinchuby added 6 commits April 18, 2025 19:11

Fix case

48bfc65

converted_proto

ec661aa

lint

a57fc86

Update ConvertVersionPass

3d1f428

comments

01ef856

remove

09d44ad

titaiwangms assigned shubhambhokare1 Apr 21, 2025

justinchuby added 4 commits April 21, 2025 15:18

Merge branch 'main' into justinchu/version-pass

baac865

test fallback

4614333

rename

188b6cb

Merge branch 'main' into justinchu/version-pass

a87b3c0

shubhambhokare1 reviewed Apr 22, 2025

View reviewed changes

onnxscript/version_converter/__init__.py Outdated Show resolved Hide resolved

onnxscript/version_converter/__init__.py Outdated Show resolved Hide resolved

Update onnxscript/version_converter/__init__.py

529ae52

Co-authored-by: Shubham Bhokare <[email protected]>

justinchuby commented Apr 22, 2025

View reviewed changes

onnxscript/version_converter/__init__.py Outdated Show resolved Hide resolved

justinchuby commented Apr 22, 2025

View reviewed changes

onnxscript/version_converter/__init__.py Outdated Show resolved Hide resolved

justinchuby added 3 commits April 22, 2025 10:16

Apply suggestions from code review

b73398e

Allow fallback

7e9ca80

log

107fb6a

justinchuby requested review from Copilot and shubhambhokare1 April 22, 2025 17:30

Copilot AI reviewed Apr 22, 2025

View reviewed changes

justinchuby added this to the 0.2.5 milestone Apr 22, 2025

arg

9ce3698

shubhambhokare1 approved these changes Apr 22, 2025

View reviewed changes

github-project-automation bot moved this from Todo to Done in ONNX Script Review Board Apr 22, 2025

justinchuby merged commit bc7671c into main Apr 22, 2025
24 of 27 checks passed

justinchuby deleted the justinchu/version-pass branch April 22, 2025 22:44

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[pass] Create version converter pass #2214

[pass] Create version converter pass #2214

Uh oh!

justinchuby commented Apr 19, 2025 •

edited

Loading

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

codecov bot commented Apr 19, 2025 •

edited

Loading

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

[pass] Create version converter pass #2214

[pass] Create version converter pass #2214

Uh oh!

Conversation

justinchuby commented Apr 19, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull Request Overview

Reviewed Changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

codecov bot commented Apr 19, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

❌ 3 Tests Failed:

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull Request Overview

Reviewed Changes

Uh oh!

Uh oh!

Uh oh!

justinchuby commented Apr 19, 2025 •

edited

Loading

codecov bot commented Apr 19, 2025 •

edited

Loading