[SOT] Add sot warmup (NVIDIA GPU Only) (#2929)

* add sot warmup

* fix code style

* change batch_size list

* add param to config

* rm free_list settings && set sot_warmup_sizes

* finish debug with dynamic dims by type annotations

* add profile_run guard

* rm sth useless

fastdeploy/config.py

@@ -319,6 +319,8 @@ class GraphOptimizationConfig:
         - With dyncmic graph backend: ...
         - With static grpah backend: WIP
     """
+    sot_warmup_sizes: Optional[list[int]] = field(default_factory=list)
+    """  Number of warmup runs for SOT warmup. """
     use_cudagraph: bool = False
     """Sizes to capture cudagraph.
     - None (default): capture sizes are inferred from llm config.