mirror of
				https://github.com/PaddlePaddle/FastDeploy.git
				synced 2025-10-31 11:56:44 +08:00 
			
		
		
		
	 48e6a0ca26
			
		
	
	48e6a0ca26
	
	
		
			
	
		
	
	
		
			Some checks failed
		
		
	
	Deploy GitHub Pages / deploy (push) Has been cancelled
				
			* [SOT] Mark dynamic dims by type annotations * fix conflict of forward_meta * mark more attn backend * fix missing annotated and add env SOT_SPECIALIZED_DIM_NUMBERS * auto infer implicit 0 dim dynamic dim * revert manual marked dims * revert missing update * auto infer can use unsafe code in warmup stage * check -> type_match * fix codestyle * restore blank line * empty commit * add need_warmup nonlocal; * add doc for resolver * add missing type hints * unquote "ForwardMeta"
		
			
				
	
	
		
			38 lines
		
	
	
		
			1.4 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
			
		
		
	
	
			38 lines
		
	
	
		
			1.4 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
| # Copyright (c) 2025 PaddlePaddle Authors. All Rights Reserved.
 | |
| #
 | |
| # Licensed under the Apache License, Version 2.0 (the "License");
 | |
| # you may not use this file except in compliance with the License.
 | |
| # You may obtain a copy of the License at
 | |
| #
 | |
| #     http://www.apache.org/licenses/LICENSE-2.0
 | |
| #
 | |
| # Unless required by applicable law or agreed to in writing, software
 | |
| # distributed under the License is distributed on an "AS IS" BASIS,
 | |
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 | |
| # See the License for the specific language governing permissions and
 | |
| # limitations under the License.
 | |
| 
 | |
| from .append_attn_backend import AppendAttentionBackend
 | |
| from .attention import Attention
 | |
| from .attention_selecter import get_attention_backend
 | |
| from .base_attention_backend import AttentionBackend
 | |
| from .block_multihead_attn_backend import BlockAttentionBackend
 | |
| from .flash_attn_backend import FlashAttentionBackend
 | |
| from .iluvatar_attn_backend import IluvatarAttnBackend
 | |
| from .mla_attention_backend import MLAAttentionBackend
 | |
| from .native_paddle_backend import PaddleNativeAttnBackend
 | |
| from .xpu_attn_backend import XPUAttentionBackend
 | |
| 
 | |
| __all__ = [
 | |
|     "AttentionBackend",
 | |
|     "PaddleNativeAttnBackend",
 | |
|     "get_attention_backend",
 | |
|     "AppendAttentionBackend",
 | |
|     "XPUAttentionBackend",
 | |
|     "MLAAttentionBackend",
 | |
|     "FlashAttentionBackend",
 | |
|     "IluvatarAttnBackend",
 | |
|     "BlockAttentionBackend",
 | |
|     "Attention",
 | |
| ]
 |