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

Runs a transposed convolution on the GPU via the cuDNN backward-data path.

Delegates the transposed convolution to cuDNN and, when an elementwise epilogue is provided, applies it as a separate elementwise pass over a temporary buffer.

Parameters:

input_type (DType): Element type of the input tensor.
filter_type (DType): Element type of the filter tensor.
output_type (DType): Element type of the output tensor.
elementwise_epilogue (Optional[def[dtype: DType, rank: Int, width: SIMDLength, alignment: Int = Int(1)](IndexList[rank], SIMD[dtype, width]) capturing thin -> None]): Optional elementwise epilogue closure applied after the convolution.

Args:

output (TileTensor[output_type, Storage=output.Storage, linear_idx_type=output.linear_idx_type]): Output tensor that receives the transposed convolution result.
input (TileTensor[input_type, Storage=input.Storage, linear_idx_type=input.linear_idx_type]): Input tensor in NHWC layout.
filter (TileTensor[filter_type, Storage=filter.Storage, linear_idx_type=filter.linear_idx_type]): Filter tensor in RSFC layout.
stride (IndexList[(input.LayoutType.rank - Int(2))]): Stride along each spatial axis.
dilation (IndexList[(input.LayoutType.rank - Int(2))]): Dilation value along each spatial axis of the filter.
padding (IndexList[(input.LayoutType.rank - Int(2))]): Padding along each spatial axis.
ctx (DeviceContext): Device context used to access the cuDNN handle and device buffers.