Mojo function

q6_k_dequantize_impl

q6_k_dequantize_impl(input_tensor: LayoutTensor[DType.uint8, input_tensor.layout, input_tensor.origin, address_space=input_tensor.address_space, element_layout=input_tensor.element_layout, layout_int_type=input_tensor.layout_int_type, linear_idx_type=input_tensor.linear_idx_type, masked=input_tensor.masked, alignment=input_tensor.alignment], output_tensor: LayoutTensor[DType.float32, output_tensor.layout, output_tensor.origin, address_space=output_tensor.address_space, element_layout=output_tensor.element_layout, layout_int_type=output_tensor.layout_int_type, linear_idx_type=output_tensor.linear_idx_type, masked=output_tensor.masked, alignment=output_tensor.alignment], output_shape: IndexList[LayoutTensor[DType.float32, output_tensor.layout, output_tensor.origin, address_space=output_tensor.address_space, element_layout=output_tensor.element_layout, layout_int_type=output_tensor.layout_int_type, linear_idx_type=output_tensor.linear_idx_type, masked=output_tensor.masked, alignment=output_tensor.alignment].rank])

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other

Submit