[Feature] Add AsyncTokenizerClient&ChatResponseProcessor with remote encode&decode support. (#3674)

* [Feature] add AsyncTokenizerClient

* add decode_image

* Add response_processors with remote decode support.

* [Feature] add tokenizer_base_url startup argument

* Revert comment removal and restore original content.

* [Feature] Non-streaming requests now support remote image decoding.

* Fix parameter type issue in decode_image call.

* Keep completion_token_ids when return_token_ids = False.

* add copyright

fastdeploy/engine/args_utils.py

@@ -71,6 +71,10 @@ class EngineArgs:
     """
     The name or path of the tokenizer (defaults to model path if not provided).
     """
+    tokenizer_base_url: str = None
+    """
+    The base URL of the remote tokenizer service (used instead of local tokenizer if provided).
+    """
     max_model_len: int = 2048
     """
     Maximum context length supported by the model.
@@ -426,6 +430,12 @@ class EngineArgs:
             default=EngineArgs.tokenizer,
             help="Tokenizer name or path (defaults to model path if not specified).",
         )
+        model_group.add_argument(
+            "--tokenizer-base-url",
+            type=nullable_str,
+            default=EngineArgs.tokenizer_base_url,
+            help="The base URL of the remote tokenizer service (used instead of local tokenizer if provided).",
+        )
         model_group.add_argument(
             "--max-model-len",
             type=int,