[bugfix][quantization] Fix fp8 per_tensor scale shape (#30257)

Signed-off-by: Haoyang Li <lihaoyang0109@gmail.com>

vllm/_custom_ops.py

@@ -1726,7 +1726,7 @@ def scaled_fp8_quant(
                 output, input, scale, scale_ub
             )
         else:
-            scale = torch.empty((1, 1), device=input.device, dtype=torch.float32)
+            scale = torch.empty(1, device=input.device, dtype=torch.float32)
             torch.ops._C.dynamic_scaled_fp8_quant(output, input, scale)
     else:
         assert scale.numel() == 1, f"{scale.shape}"