[Enhance] The argument scale of fused_bias_leakyrelu should be greater than 0 (#2623)

* Add verification for scale, when scale less than 0

* Update mmcv/ops/fused_bias_leakyrelu.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* Update fused_bias_leakyrelu.py

* Update fused_bias_leakyrelu.py

---------
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

mmcv/ops/fused_bias_leakyrelu.py

@@ -257,7 +257,7 @@ def fused_bias_leakyrelu(input: torch.Tensor,
     Returns:
         torch.Tensor: Feature map after non-linear activation.
     """
-
+    assert scale > 0, 'The scale should be greater than 0'
     if not input.is_cuda and input.device.type != 'npu':
         return bias_leakyrelu_ref(input, bias, negative_slope, scale)