update max_seq_len_to_capture to int

vllm/config.py

@@ -313,8 +313,7 @@ class ModelConfig:
     graph and always execute the model in eager mode. If False, we will use
     CUDA graph and eager execution in hybrid for maximal performance and
     flexibility."""
-    # max_seq_len_to_capture: int = 8192
-    max_seq_len_to_capture: bool = None
+    max_seq_len_to_capture: int = None # 8192
     """Maximum sequence len covered by CUDA graphs. When a sequence has context
     length larger than this, we fall back to eager mode. Additionally for
     encoder-decoder models, if the sequence length of the encoder input is