Mila 0.13.48
Deep Neural Network Library
Loading...
Searching...
No Matches
Mila::Dnn::Quant::Weight::NoWeightQuant Struct Referenceexport

Static Public Attributes

static constexpr bool kIsQuantized = false
static constexpr bool kPerChannel = false
static constexpr TensorDataType kScaleDtype = TensorDataType::FP32
static constexpr TensorDataType kStorageDtype = TensorDataType::FP32

Member Data Documentation

◆ kIsQuantized

bool Mila::Dnn::Quant::Weight::NoWeightQuant::kIsQuantized = false
staticconstexpr

◆ kPerChannel

bool Mila::Dnn::Quant::Weight::NoWeightQuant::kPerChannel = false
staticconstexpr

◆ kScaleDtype

TensorDataType Mila::Dnn::Quant::Weight::NoWeightQuant::kScaleDtype = TensorDataType::FP32
staticconstexpr

◆ kStorageDtype

TensorDataType Mila::Dnn::Quant::Weight::NoWeightQuant::kStorageDtype = TensorDataType::FP32
staticconstexpr

The documentation for this struct was generated from the following file:
  • /__w/Mila/Mila/Mila/Src/Dnn/Quantization/Weight/Policies.ixx