[Optimization] Support FA2/FA3/FA4 with attn_mask_q (#6354)

* support FA4 sm100

* flash attn backend support mask

* flash attn backend run flashmask correct

* add test for flash_attn_backend and flash_attn_func

* check

* add test for fa4

* requirements.txt add fa4 whl

* check test on sm100

* fix CI conflict

* add enable_torch_proxy for flash_mask

* lazy import fa4

* check

* fix tests import

* check test_load_mpt import

fastdeploy/model_executor/utils.py

@@ -19,6 +19,7 @@ import re
 from collections.abc import Mapping
 from contextlib import contextmanager
 from dataclasses import dataclass, field
+from functools import cache
 from typing import Any, List, Optional, Union
 
 import paddle
@@ -547,3 +548,11 @@ def rename_offline_ckpt_suffix_to_fd_suffix(
         return loaded_weight_name
 
     return fn
+
+
+@cache
+def get_sm_version():
+    if paddle.cuda.is_available():
+        prop = paddle.device.cuda.get_device_properties()
+        return prop.major * 10 + prop.minor
+    return 0