CublasLtMatMulBias.ixx File Reference

#include <cublasLt.h>
#include <cuda_fp16.h>
#include <cuda_bf16.h>
#include <cuda_fp8.h>
#include <type_traits>
import Utils.Logger;
import CublasLt.Error;
import Cuda.DataTypeTraits;

Namespaces
namespace	Mila
namespace	Mila::Dnn
namespace	Mila::Dnn::Compute

Functions
template<typename TDataType , typename TCompute = float> requires std::is_same_v<TDataType, float> || std::is_same_v<TDataType, half> || std::is_same_v<TDataType, __nv_bfloat16> || std::is_same_v<TDataType, __nv_fp8_e4m3>
void	Mila::Dnn::Compute::cublaslt_matmul_forward (TDataType *Y, const TDataType *X, const TDataType *weight, const TDataType *bias, int outer_size, int C, int OC, cudaStream_t stream, cublasLtHandle_t cublasLtHandle)
	cuBLASLt implementation of matrix multiplication with bias addition

Variables
template<typename T >
constexpr bool	Mila::Dnn::Compute::always_false = false