Release/2.1 (#3414)

* Pre ce modified (#3335) (#3360)

* Pre ce modified (#3335)

* update

* update

* fix

* fix

* update

* update

* update

* fix

* update

* update

* update

* add ut fix pr(3367)

* [Bug Fix] Fix V1 video bug (#3387)

* fix stopseq error info (#3342)

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>

* [BugFix] Fix default log level of paddleformers (#3377)

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>

* [Polish Code] Remove useless notes

* feat(log):add_request_and_response_log (#3392)

* Optimize CI execution workflow. (#3371) (#3384)

* fix

* [BugFix] fix control signal release failed (#3374)

* [BugFix]

* [BugFix]

* [BugFix]

* [BugFix]

* fix

* fix

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

* Revert "Merge branch 'feature/online/vs_think_20250813' into release/2.1"

This reverts commit 02596fc537, reversing
changes made to 03347626a6.

* [XPU] Fixed the issue of performance degradation caused by enabling ENABLE_V1_KVCACHE_SCHEDULER (#3393)

* fix v1 schedule oom bug

* fix v1 schedule oom bug

* [BugFix] fix ErnieProcessor not set raw_prediction (#3401)

* [Doc]Release fastdeploy-xpu 2.1.0 (#3407)

* fix v1 schedule oom bug

* fix v1 schedule oom bug

* update release note

* [Doc]Release fastdeploy-xpu 2.0.3  (#3408)

* fix v1 schedule oom bug

* fix v1 schedule oom bug

* update release note

* update info

---------

Co-authored-by: YUNSHEN XIE <1084314248@qq.com>
Co-authored-by: ming1753 <61511741+ming1753@users.noreply.github.com>
Co-authored-by: JYChen <zoooo0820@qq.com>
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <jiangjiajun@baidu.com>
Co-authored-by: xiaolei373 <zley373@gmail.com>
Co-authored-by: ltd0924 <32387785+ltd0924@users.noreply.github.com>
Co-authored-by: yinwei <yinwei_hust@163.com>
Co-authored-by: memoryCoderC <1137889088@qq.com>

fastdeploy/input/preprocess.py

@@ -18,7 +18,6 @@ from typing import Any, Dict, Optional
 
 from fastdeploy.config import ErnieArchitectures
 from fastdeploy.engine.config import ModelConfig
-from fastdeploy.entrypoints.openai.tool_parsers import ToolParserManager
 from fastdeploy.reasoning import ReasoningParserManager
 
 
@@ -49,7 +48,6 @@ class InputPreprocessor:
         limit_mm_per_prompt: Optional[Dict[str, Any]] = None,
         mm_processor_kwargs: Optional[Dict[str, Any]] = None,
         enable_mm: bool = False,
-        tool_parser: str = None,
     ) -> None:
 
         self.model_name_or_path = model_name_or_path
@@ -57,7 +55,6 @@ class InputPreprocessor:
         self.enable_mm = enable_mm
         self.limit_mm_per_prompt = limit_mm_per_prompt
         self.mm_processor_kwargs = mm_processor_kwargs
-        self.tool_parser = tool_parser
 
     def create_processor(self):
         """
@@ -71,11 +68,8 @@ class InputPreprocessor:
             DataProcessor or MultiModalRegistry.Processor (Union[DataProcessor, MultiModalRegistry.Processor]): 数据处理器。
         """
         reasoning_parser_obj = None
-        tool_parser_obj = None
         if self.reasoning_parser:
             reasoning_parser_obj = ReasoningParserManager.get_reasoning_parser(self.reasoning_parser)
-        if self.tool_parser:
-            tool_parser_obj = ToolParserManager.get_tool_parser(self.tool_parser)
         architectures = ModelConfig({"model": self.model_name_or_path}).architectures[0]
         if not self.enable_mm:
             if not ErnieArchitectures.contains_ernie_arch(architectures):
@@ -84,7 +78,6 @@ class InputPreprocessor:
                 self.processor = DataProcessor(
                     model_name_or_path=self.model_name_or_path,
                     reasoning_parser_obj=reasoning_parser_obj,
-                    tool_parser_obj=tool_parser_obj,
                 )
             else:
                 from fastdeploy.input.ernie_processor import ErnieProcessor
@@ -92,7 +85,6 @@ class InputPreprocessor:
                 self.processor = ErnieProcessor(
                     model_name_or_path=self.model_name_or_path,
                     reasoning_parser_obj=reasoning_parser_obj,
-                    tool_parser_obj=tool_parser_obj,
                 )
         else:
             if not architectures.startswith("Ernie4_5_VLMoeForConditionalGeneration"):
@@ -105,6 +97,5 @@ class InputPreprocessor:
                     limit_mm_per_prompt=self.limit_mm_per_prompt,
                     mm_processor_kwargs=self.mm_processor_kwargs,
                     reasoning_parser_obj=reasoning_parser_obj,
-                    tool_parser_obj=tool_parser_obj,
                 )
         return self.processor