triton.language.dot

triton.language.dot(input, other, allow_tf32=True, out_dtype=triton.language.fp32)

Returns the matrix product of two blocks.

The two blocks must be two-dimensional and have compatible inner dimensions.

Parameters:
  • input (2D tensor of scalar-type in {float16, bfloat16, float32}) – The first tensor to be multiplied.

  • other (2D tensor of scalar-type in {float16, bfloat16, float32}) – The second tensor to be multiplied.