ttnn.interleaved_to_sharded_partial

ttnn.interleaved_to_sharded_partial = FastOperation(python_fully_qualified_name='ttnn.interleaved_to_sharded_partial', function=<ttnn._ttnn.operations.data_movement.interleaved_to_sharded_partial_t object>, preprocess_golden_function_inputs=<function default_preprocess_golden_function_inputs>, golden_function=<function _golden_function>, postprocess_golden_function_outputs=<function default_postprocess_golden_function_outputs>, is_cpp_operation=True, is_experimental=False)

Converts a partial tensor from interleaved to sharded memory layout

:param * input_tensor: input tensor :type * input_tensor: ttnn.Tensor :param * grid: Grid of sharded tensor :type * grid: ttnn.CoreGrid :param * num_slices: Number of slices. :type * num_slices: int :param * slice_index: Slice index. :type * slice_index: int :param * shard_scheme: Sharding scheme(height, width or block). :type * shard_scheme: ttl.tensor.TensorMemoryLayout :param * shard_orienttion: Shard orientation (ROW or COL major). :type * shard_orienttion: ttl.tensor.ShardOrientation

:keyword * output_dtype: Output data type, defaults to same as input. :kwtype * output_dtype: Optional[ttnn.DataType]

Example

>>> sharded_tensor = ttnn.sharded_to_interleaved(tensor, ttnn.CoreGrid(3,3), 2, 2, ttl.tensor.TensorMemoryLayout.HEIGHT_SHARDED, ttl.tensor.ShardOrientation.ROW_MAJOR)