MNN:Sync: Sync Internal 3.3.0 #3986
                
     Merged
            
            
          
      
        
          +35,837
        
        
          −21,779
        
        
          
        
      
    
  
  Add this suggestion to a batch that can be applied as a single commit.
  This suggestion is invalid because no changes were made to the code.
  Suggestions cannot be applied while the pull request is closed.
  Suggestions cannot be applied while viewing a subset of changes.
  Only one suggestion per line can be applied in a batch.
  Add this suggestion to a batch that can be applied as a single commit.
  Applying suggestions on deleted lines is not supported.
  You must change the existing code in this line in order to create a valid suggestion.
  Outdated suggestions cannot be applied.
  This suggestion has been applied or marked resolved.
  Suggestions cannot be applied from pending reviews.
  Suggestions cannot be applied on multi-line comments.
  Suggestions cannot be applied while the pull request is queued to merge.
  Suggestion cannot be applied right now. Please check back later.
  
    
  
    
一、大语言模型(LLM)能力增强
● 新增模型支持:
● LLM 推理优化:
● 量化与精度:
二、硬件加速与 NPU 支持
● CPU 加速:
● CUDA 后端支持LLM:
● GPU 后端修复:
● NPU 支持LLM:
三、框架功能与稳定性提升
● 核心框架改进:
● Python 兼容性:
● 模型转换优化:
四、开源社区与兼容性
● 修复多个社区反馈问题(Issue #3623、#3632、#3690、#3701、#3774、#3780、#3850 等)。
● 提升跨平台兼容性,包括 Windows ARM、macOS、Android、iOS、鸿蒙等。
MNN 3.3 版本持续聚焦 端侧大模型高效推理 与 多硬件平台统一部署,并积极回馈开源社区。