For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

Mojo function

conv_transposed_gpu

def conv_transposed_gpu[input_type: DType, filter_type: DType, output_type: DType, elementwise_epilogue: Optional[def[dtype: DType, rank: Int, width: SIMDSize, alignment: Int = Int(1)](IndexList[rank], SIMD[dtype, width]) capturing -> None] = None](output: TileTensor[output_type, Storage=output.Storage, linear_idx_type=output.linear_idx_type, element_size=output.element_size], input: TileTensor[input_type, Storage=input.Storage, linear_idx_type=input.linear_idx_type, element_size=input.element_size], filter: TileTensor[filter_type, Storage=filter.Storage, linear_idx_type=filter.linear_idx_type, element_size=filter.element_size], stride: IndexList[(input.LayoutType.rank - Int(2))], dilation: IndexList[(input.LayoutType.rank - Int(2))], padding: IndexList[(input.LayoutType.rank - Int(2))], ctx: DeviceContext)