fix comment

Signed-off-by: Bill Nell <bnell@redhat.com>

Author: bnellnm

vllm/_custom_ops.py

@@ -1274,7 +1274,6 @@ def scaled_fp8_quant(
             scale = torch.zeros(1, device=input.device, dtype=torch.float32)
             torch.ops._C.dynamic_scaled_fp8_quant(output, input, scale)
     else:
-        # num_token_padding not implemented for this case
         assert scale.numel() == 1, f"{scale.shape}"
         torch.ops._C.static_scaled_fp8_quant(output, input, scale)