[MetaxGPU] Support FastDeploy on metax gpu (#3241)

* [MetaxGPU] Support FastDeploy on metax gpu

* Update metax_worker.py

1. change worker log;
2. remove custom allreduce, adapt it later;
3. remove cuda graph;

* Update __init__.py

1. remove metax's key work comment

* Update __init__.py

1. remove metax's key word comment;
2. add fused_moe_kernel_paddle import

---------

Co-authored-by: yongqiangma <xing.wo@163.com>

fastdeploy/model_executor/forward_meta.py

@@ -37,6 +37,8 @@ class ForwardMode(IntEnum):
     DECODE = auto()
     # Mixed mode
     MIXED = auto()
+    # Native mode
+    NATIVE = auto()
 
     def is_prefill(self):
         """Is Extend mode"""
@@ -50,6 +52,10 @@ class ForwardMode(IntEnum):
         """Is Mixed mode"""
         return self == ForwardMode.MIXED
 
+    def is_native(self):
+        """Is Native mode"""
+        return self == ForwardMode.NATIVE
+
 
 @dataclass
 class ForwardMeta: