Mila 0.13.48
Deep Neural Network Library
Loading...
Searching...
No Matches
CpuSoftmaxOp.ixx File Reference

CPU implementation of Softmax operation (TensorDataType-based). More...

#include <memory>
#include <vector>
#include <string>
#include <stdexcept>
#include <math.h>
#include <cmath>
#include <cstdint>
#include <limits>
import Compute.OperationBase;
import Compute.CpuTensorDataTypeTraits;
import Dnn.Components.SoftmaxConfig;
import Dnn.Component;
import Compute.ExecutionContext;
import Compute.CpuDevice;
import Compute.CpuMemoryResource;
import Dnn.TensorTypes;
import Compute.IExecutionContext;
import Compute.UnaryOperation;
import Dnn.TensorDataType;
import Dnn.Tensor;
import Dnn.TensorDataTypeTraits;
import Dnn.TensorHostTypeMap;
import Dnn.TensorPartitioning;
import Dnn.ComponentConfig;
import Compute.OperationRegistry;
import Dnn.ITensor;
import Compute.DeviceType;
import Compute.MemoryResource;
import Compute.OperationType;

Classes

class  Mila::Dnn::Compute::CpuSoftmaxOp
 CPU implementation of Softmax using abstract TensorDataType API. More...
class  Mila::Dnn::Compute::CpuSoftmaxOpRegistrar

Namespaces

namespace  Mila
 Mila main API namespace.
namespace  Mila::Dnn
namespace  Mila::Dnn::Compute

Detailed Description

CPU implementation of Softmax operation (TensorDataType-based).

Ported to the ExecutionContext / TensorDataType UnaryOperation interface following the two-phase initialization pattern used by CpuLayerNormOp.