.xoptim.patterns_ort¶

modules

experimental_experiment.xoptim.patterns_ort.get_onnxruntime_patterns(verbose: int = 0) → List[PatternOptimization][source]¶

Returns a default list of optimization patterns for onnxruntime. It is equal to the following list.

<<<

from experimental_experiment.xoptim.patterns_api import pattern_table_doc
from experimental_experiment.xoptim.patterns_ort import get_onnxruntime_patterns

print(pattern_table_doc(get_onnxruntime_patterns(), as_rst=True))

>>>

	name	short_name	priority	doc
0	BiasGeluPattern	BiasGelu	1	Replaces by `y = BiasGelu(x, B)`
1	BiasSoftmaxPattern	BiasSoftmax	1	Replaces Softmax(Add(x,y), axis=-1) by BiasSoftmax(x,y,axis=-1)
2	GeluOrtPattern	GeluOrt	0	Detects the decomposed version of Gelu with Tanh .. math
3	GeluErfPattern	GeluErf	0	Detects the decomposed version of Gelu with Erf.
4	FusedConvPattern	FusedConv	2	Replaces the Conv + Relu into FusedConv.
5	FastGeluPattern	FastGelu	1	Replaces Gelu by FastGelu.
6	FusedMatMulPattern	FusedMatMul	2	Replaces the sequence Transpose, Matmul into FusedMatMul.
7	FusedMatMulx2Pattern	FusedMatMulx2	3	Replaces the sequence Div by a scalar consumed by two FusedMatMul.
8	FusedMatMulDivPattern	FusedMatMulDiv	2	Replaces the Matmul, Div into FusedMatMul.
9	FusedMatMulTransposePattern	FusedMatMulTranspose	3	Replaces the sequence (Fused)Matmul(A,B) + Transpose into FusedMatMul(B.T, A.T).
10	OrtBatchNormalizationTrainingPattern	OrtBatchNormalizationTraining	1	onnxruntime does not support batch normalization with training=1.
11	QuickGeluPattern	QuickGelu	1	Replaces Mul(x, Sigmoid(x)) by QuickGelu(x, alpha=1)
12	SimplifiedLayerNormalizationPattern	SimplifiedLayerNormalization	1	Replaces the sequence Transpose, Matmul into FusedMatMul.
13	SoftmaxGradPattern	SoftmaxGrad	1	Replaces the sequence Mul, ReduceSum, Mul, Sub by SoftmaxGrad