experimental_experiment.xoptim.patterns_exp

experimental_experiment.xoptim.patterns_exp.get_experimental_patterns(verbose: int = 0) List[PatternOptimization][source]

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

<<<

import pprint
from experimental_experiment.xoptim.patterns_exp import (
    get_experimental_patterns,
)

pprint.pprint(get_experimental_patterns())

>>>

    [AddAddMulMulPattern(),
     AddAddMulMulBroadcastPattern(),
     AddMulPattern(),
     AddMulBroadcastPattern(),
     AddMulSharedInputPattern(),
     AddMulSharedInputBroadcastPattern(),
     AddMulTransposePattern(),
     ConstantOfShapeScatterNDPattern(),
     MaskedShapeScatterNDPattern(),
     MulSigmoidPattern(),
     NegXplus1Pattern(),
     ReplaceZeroPattern(),
     SimpleRotaryPattern(),
     SubMulPattern(),
     SubMulBroadcastPattern(),
     TransposeCastPattern(),
     TriMatrixPattern()]