Update modeling_llava_qwen2.py

modeling_llava_qwen2.py

@@ -2090,7 +2090,7 @@ class Qwen2ForCausalLM(Qwen2PreTrainedModel):
             if isinstance(past_key_values, Cache):
                 cache_length = past_key_values.get_seq_length()
                 past_length = past_key_values.seen_tokens
-                max_cache_length = past_key_values.get_max_length()
+                max_cache_length = past_key_values.get_max_length() if hasattr(past_key_values, "get_max_length") else past_key_values.get_max_cache_shape()
             else:
                 cache_length = past_length = past_key_values[0][0].shape[2]
                 max_cache_length = None