# tensorplay.backends.cuda.allow_fp16_bf16_reduction_math_sdp

Source: https://www.tensorplay.cn/docs/generated/tensorplay.backends.cuda.allow_fp16_bf16_reduction_math_sdp.html

```python
tensorplay.backends.cuda.allow_fp16_bf16_reduction_math_sdp(enabled: bool)
```

> **Warning**
>
> This flag is beta and subject to change.

Enables or disables fp16/bf16 reduction in math scaled dot product attention.