[Optimization]Unified data processing for online and offline (#6891)

* remove process_request

* fix chat

* fix unit test

* remove process response

* fix unit test

* fix offline decode

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* fix sampling_params

---------

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

fastdeploy/input/qwen_vl_processor/qwen_vl_processor.py

@@ -16,7 +16,6 @@
 
 import numpy as np
 
-from fastdeploy.engine.request import Request
 from fastdeploy.input.text_processor import DataProcessor as TextProcessor
 from fastdeploy.input.utils import process_stop_token_ids
 from fastdeploy.utils import data_processor_logger
@@ -75,25 +74,6 @@ class QwenVLProcessor(TextProcessor):
         self.image_patch_id = self.processor.image_token_id
         self.limit_mm_per_prompt = self._parse_limits(limit_mm_per_prompt)
 
-    def process_request(self, request, max_model_len=None, **kwargs):
-        """
-        Process incoming request and generate model inputs.
-
-        Args:
-            request: Input request object
-            max_model_len (int, optional): Maximum context length
-            **kwargs: Additional processing parameters
-
-        Returns:
-            Request: Processed request with model inputs
-        """
-        task = request.to_dict()
-        task["enable_thinking"] = kwargs.get("enable_thinking", False)
-        self.process_request_dict(task, max_model_len)
-        request = Request.from_dict(task)
-        request = self._apply_default_parameters(request)
-        return request
-
     def _parse_processor_kwargs(self, kwargs):
         """
         Parse and validate multimodal processor arguments.