What does this PR do?

fix scaled_dot_product_attention api dtype bug, or "TypeError: for primitive [BatchMatMul] input type must be same" if configure decoder_attn_dtype=fp16 in first_stage_config.

# sdxl infer with yaml:
    first_stage_config:
      target: gm.models.autoencoder.AutoencoderKLInferenceWrapper
      params:
          ...
          decoder_attn_dtype: fp16

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline?
• Did you make sure to update the documentation with your changes? E.g. record bug fixes or new features in What's New. Here are the
  documentation guidelines
• Did you build and run the code without any errors?
• Did you report the running environment (NPU type/MS version) and performance in the doc? (better record it for data loading, model inference, or training tasks)
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.