[Executor] Default use CUDAGraph (#3594)

* add start intercept

* Adjustment GraphOptConfig

* pre-commit

* default use cudagraph

* set default value

* default use cuda graph

* pre-commit

* fix test case bug

* disable rl

* fix moba attention

* only support gpu

* Temporarily disable PD Disaggregation

* set max_num_seqs of test case as 1

* set max_num_seqs and temperature

* fix max_num_batched_tokens bug

* close cuda graph

* success run wint2

* profile run with max_num_batched_tokens

* 1.add c++ memchecker 2.success run wint2

* updatee a800 yaml

* update docs

* 1. delete check 2. fix plas attn test case

* default use use_unique_memory_pool

* add try-except for warmup

* ban mtp, mm, rl

* fix test case mock

* fix ci bug

* fix form_model_get_output_topp0 bug

* fix ci bug

* refine deepseek ci

* refine code

* Disable PD

* fix sot yaml

fastdeploy/engine/args_utils.py

@@ -354,10 +354,6 @@ class EngineArgs:
     """
     SplitWise Use, Results Writer Batch Size
     """
-    use_cudagraph: bool = False
-    """
-    Flags to enable Cuda Graph
-    """
     graph_optimization_config: Optional[Dict[str, Any]] = None
     """
     Configuration for graph optimization backend execution.
@@ -586,17 +582,11 @@ class EngineArgs:
             "is lower than that of the config file. "
             "More complex quantization methods need to be configured via the config file.",
         )
-        model_group.add_argument(
-            "--use-cudagraph",
-            action="store_true",
-            default=EngineArgs.use_cudagraph,
-            help="Flags to enable cuda graph.",
-        )
         model_group.add_argument(
             "--graph-optimization-config",
             type=json.loads,
             default=EngineArgs.graph_optimization_config,
-            help="",
+            help="Configuration for graph optimization",
         )
         model_group.add_argument(
             "--plas-attention-config",
@@ -1057,7 +1047,6 @@ class EngineArgs:
         parallel_cfg = ParallelConfig(all_dict)
         scheduler_cfg = self.create_scheduler_config()
         graph_opt_cfg = self.create_graph_optimization_config()
-        graph_opt_cfg.update_use_cudagraph(self.use_cudagraph)
         plas_attention_config = self.create_plas_attention_config()
 
         early_stop_cfg = self.create_early_stop_config()