Mila
Deep Neural Network Library
|
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 | |
Files | |
file | /home/runner/work/Mila/Mila/Mila/Src/Dnn/Compute/Operations/Cuda/CublasLtMatMulBias.ixx |