Skip to content

Cleanup mha-bias rules using disjunction #2326

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.

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

Merged
merged 1 commit into from
May 22, 2025
Merged

Conversation

gramalingam
Copy link
Collaborator

The MHA-Bias rules can be simplified using pattern-disjunction.

(This may help with Whisper ... that was my original motivation, but not sure, after I fixed another issue in PR #2325, which may be the primary issue ). But the cleanup is useful anyway, and it makes fusion more efficient.)

Copy link

codecov bot commented May 22, 2025

❌ 11 Tests Failed:

Tests completed Failed Passed Skipped
16727 11 16716 2524
View the top 3 failed test(s) by shortest run time
onnxscript.backend.onnx_export_test.TestOnnxBackEnd::test_export2python_produces_correct_onnx_script_model_0216_test_bitwise_not_2d
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_bitwise_not_2d'

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_bitwise_not_2d' (e=No module named 'tests.onnx_backend_test_code.test_bitwise_not_2d') (file: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_bitwise_not_2d.py', absolute path: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_bitwise_not_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_not_2d(x: INT32[3,4]) -> (INT32[3,4]):
E       bitwise_not = opset18.BitwiseNot(x)
E       return bitwise_not
onnxscript.backend.onnx_export_test.TestOnnxBackEnd::test_export2python_produces_correct_onnx_script_model_0871_test_reduce_max_keepdims_example
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_reduce_max_keepdims_example'

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_reduce_max_keepdims_example' (e=No module named 'tests.onnx_backend_test_code.test_reduce_max_keepdims_example') (file: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_reduce_max_keepdims_example.py', absolute path: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_reduce_max_keepdims_example.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 opset18
E   
E   @script()
E   def bck_test_reduce_max_keepdims_example(data: FLOAT[3,2,2], axes: INT64[1]) -> (FLOAT[3,1,2]):
E       reduced = opset18.ReduceMax(data, axes, keepdims=1)
E       return reduced
onnxscript.backend.onnx_export_test.TestOnnxBackEnd::test_export2python_produces_correct_onnx_script_model_1134_test_softmax_axis_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\3.10.11\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_softmax_axis_1'

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_softmax_axis_1' (e=No module named 'tests.onnx_backend_test_code.test_softmax_axis_1') (file: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_softmax_axis_1.py', absolute path: 'D:\\a\\onnxscript\\onnxscript\\tests\\onnx_backend_test_code\\test_softmax_axis_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 FLOAT
E   from onnxscript.onnx_opset import opset13
E   
E   @script()
E   def bck_test_softmax_axis_1(x: FLOAT[3,4,5]) -> (FLOAT[3,4,5]):
E       y = opset13.Softmax(x, axis=1)
E       return y

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

@justinchuby justinchuby merged commit 7aba165 into main May 22, 2025
23 of 29 checks passed
@justinchuby justinchuby deleted the rama/mha-bias-or-cleanup branch May 22, 2025 14:39
bmehta001 pushed a commit to bmehta001/onnxscript that referenced this pull request May 22, 2025
The MHA-Bias rules can be simplified using pattern-disjunction.

(This _may_ help with Whisper ... that was my original motivation, but
not sure, after I fixed another issue in PR microsoft#2325, which may be the
primary issue ). But the cleanup is useful anyway, and it makes fusion
more efficient.)

Signed-off-by: Ganesan Ramalingam <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Development

Successfully merging this pull request may close these issues.

2 participants