8000 Clean up backend tests for reference runtime by justinchuby · Pull Request #7107 · onnx/onnx · GitHub
[go: up one dir, main page]
Skip to content

Clean up backend tests for reference runtime #7107

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Clean up backend tests for reference runtime #7107

wants to merge 1 commit into from

Conversation

@justinchuby
Copy link
Member
@justinchuby justinchuby commented Jul 3, 2025

Un-skip the skipped tests.

@justinchuby
Clean up backend tests for reference runtime
105c1d0 
Signed-off-by: Justin Chu <justinchuby@users.noreply.github.com>
@justinchuby justinchuby requested a review from a team as a code owner July 3, 2025 18:23
@github-project-automation github-project-automation bot moved this to In progress in PR Tracker Jul 3, 2025
@codecov
Copy link
codecov bot commented Jul 3, 2025 •
edited
Loading

❌ 7 Tests Failed:

Tests completed Failed Passed Skipped
5065 7 5058 3440
View the top 3 failed test(s) by shortest run time 
onnx.test.test_backend_reference.OnnxBackendSimpleModelTest::test_gradient_of_add_and_mul_cpu
Stack Traces | 0.001s run time 
onnx\backend\test\runner\__init__.py:392: in run
    prepared_model = self.backend.prepare(model, device, **kwargs)
onnx\test\test_backend_reference.py:75: in prepare
    inf = cls.create_inference_session(model)
onnx\test\test_backend_reference.py:64: in create_inference_session
    return ReferenceEvaluator(model)
onnx\reference\reference_evaluator.py:305: in __init__
    self._init()
onnx\reference\reference_evaluator.py:422: in _init
    cl = self._load_impl(node)
onnx\reference\reference_evaluator.py:508: in _load_impl
    return load_op_pt(node.domain, node.op_type, version)
onnx\reference\ops\aionnx_preview_training\_op_list.py:53: in load_op
    raise NotImplementedError(
E   NotImplementedError: No registered implementation for operator 'Gradient' and domain 'ai.onnx.preview.training' in
E   Adagrad, Adam, Momentum, OpFunction, OpRun
onnx.test.test_backend_reference.OnnxBackendNodeModelTest::test_scan_sum_cpu
Stack Traces | 0.002s run time 
onnx\backend\test\runner\__init__.py:483: in run
    outputs = list(prepared_model.run(inputs))
onnx\test\test_backend_reference.py:48: in run
    outs = self._session.run(None, feeds)
onnx\reference\reference_evaluator.py:594: in run
    outputs = node.run(*inputs, **linked_attributes)
onnx\reference\op_run.py:462: in run
    res = self._run(*args, **kwargs)
onnx\reference\ops\op_scan.py:136: in _run
    outputs_list = self._run_body(inputs)
onnx\reference\op_run.py:253: in <lambda>
    attributes=None: OpRun._evaluate_subgraph(
onnx\reference\op_run.py:230: in _evaluate_subgraph
  
8000
  return value.run(None, context or {}, attributes=attributes)
onnx\reference\reference_evaluator.py:582: in run
    raise RuntimeError(
E   RuntimeError: Unable to find input 'next' in known results ['', 'sum_in'], self.rt_inits_ has [], feed_inputs has ['sum_in'].
onnx.test.test_backend_reference.OnnxBackendSimpleModelTest::test_gradient_of_add_cpu
Stack Traces | 0.002s run time 
onnx\backend\test\runner\__init__.py:392: in run
    prepared_model = self.backend.prepare(model, device, **kwargs)
onnx\test\test_backend_reference.py:75: in prepare
    inf = cls.create_inference_session(model)
onnx\test\test_backend_reference.py:64: in create_inference_session
    return ReferenceEvaluator(model)
onnx\reference\reference_evaluator.py:305: in __init__
    self._init()
onnx\reference\reference_evaluator.py:422: in _init
    cl = self._load_impl(node)
onnx\reference\reference_evaluator.py:508: in _load_impl
    return load_op_pt(node.domain, node.op_type, version)
onnx\reference\ops\aionnx_preview_training\_op_list.py:53: in load_op
    raise NotImplementedError(
E   NotImplementedError: No registered implementation for operator 'Gradient' and domain 'ai.onnx.preview.training' in
E   Adagrad, Adam, Momentum, OpFunction, OpRun

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

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

module: reference implementation

Projects

PR Tracker
Status: In progress

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@justinchuby
0