fix patch bug

Signed-off-by: wangxiyuan <[email protected]>

Author: wangxiyuan

vllm_ascend/patch/worker/patch_common/patch_attention_layer.py

@@ -196,6 +196,7 @@ def __init__(
         self.q_range = torch.tensor(envs.Q_SCALE_CONSTANT, dtype=torch.float32)
         self.k_range = torch.tensor(envs.K_SCALE_CONSTANT, dtype=torch.float32)
         self.v_range = torch.tensor(envs.V_SCALE_CONSTANT, dtype=torch.float32)
+        self.query_quant = None
 
 
 vllm.attention.Attention = AscendAttention