Mila::Dnn::Quant::Weight::PerChannelFp8< TStorage > Struct Template Reference

Static Public Attributes
static constexpr bool	kIsQuantized = true
static constexpr bool	kPerChannel = true
static constexpr TensorDataType	kScaleDtype = TensorDataType::FP32
static constexpr TensorDataType	kStorageDtype = TStorage

---

The documentation for this struct was generated from the following file:

• Mila/Src/Dnn/Quantization/Weight/Policies.ixx