experimental_experiment.xoptim.patterns_ort¶
- experimental_experiment.xoptim.patterns_ort.activation
- experimental_experiment.xoptim.patterns_ort.activation_grad
- experimental_experiment.xoptim.patterns_ort.fused_conv
- experimental_experiment.xoptim.patterns_ort.fused_matmul
- experimental_experiment.xoptim.patterns_ort.gather_grad
- experimental_experiment.xoptim.patterns_ort.simplified_layer_normalization
- 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.
<<<
import pprint from experimental_experiment.xoptim.patterns_ort import get_onnxruntime_patterns pprint.pprint(get_onnxruntime_patterns())
>>>
[BiasGeluPattern(), BiasSoftmaxPattern(), GeluOrtPattern(), GeluErfPattern(), FusedConvPattern(), FastGeluPattern(), FusedMatMulPattern(), FusedMatMulx2Pattern(), FusedMatMulDivPattern(), FusedMatMulTransposePattern(), SimplifiedLayerNormalizationPattern(), SoftmaxGradPattern()]