asc.experimental.asctile.full

asc.experimental.asctile.full(shape: Iterable[int], value: PlainValue | int | float, dtype: DataType | None = None) → LocalTensor

Create a tensor filled with a scalar value.

The supported data types are: int8, int16, int32, int64, float16, bfloat16, float32.

Parameters:

• shape – The shape of the tensor to create.

• value – The scalar value to fill the tensor with.

• dtype – The data type of the tensor. If None, inferred from the value type.

Returns:

A new tensor filled with the specified value

Return type:

LocalTensor

Raises:

• TypeError – If value is not a numeric type or dtype is not a DataType

• RuntimeError – If shape is invalid or dtype is not supported

Examples

Create a tensor filled with a constant integer value:

result = asctile.full([128], 42, dtype=asctile.int32)

Create a tensor filled with a floating-point value:

result = asctile.full([32, 16], 3.14, dtype=asctile.float16)

Create a tensor with dtype inferred from the value:

result = asctile.full([64], 0)       # inferred as int32
result = asctile.full([64], 1.5)     # inferred as float32