afe.tvm_converter.parameters

Global parameters to the TVM converter. This holds data that is passed to the converter and is globally available during the TVM converter.

Classes

TVMConverterParams

Parameters to an invocation of the TVM converter. These parameters

Module Contents

class afe.tvm_converter.parameters.TVMConverterParams[source]

Parameters to an invocation of the TVM converter. These parameters control how to convert a Relay IR module to an AwesomeNet.

Parameters:

  • requantization_mode – Requantization mode to use when translating quantized operators.

  • is_quantized – Whether the module is already quantized. If true, then the translation will not prepare for the SiMa IR quantization pass to run afterward.

  • target – A target platform that a model is compiled for.

requantization_mode: afe.ir.defines.RequantizationMode[source]
is_quantized: bool = False[source]
target: sima_utils.common.Platform[source]