[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

custom_ops/setup_ops.py

@@ -251,6 +251,7 @@ if paddle.is_compiled_with_rocm():
     )
 elif paddle.is_compiled_with_cuda():
     sources = [
+        "gpu_ops/helper.cu",
         "gpu_ops/save_with_output_msg.cc",
         "gpu_ops/get_output.cc",
         "gpu_ops/get_output_msg_with_topk.cc",
@@ -499,7 +500,7 @@ elif paddle.is_compiled_with_cuda():
             sources=sources,
             extra_compile_args={"cxx": cc_compile_args, "nvcc": nvcc_compile_args},
             libraries=["cublasLt"],
-            extra_link_args=["-lcuda"],
+            extra_link_args=["-lcuda", "-lnvidia-ml"],
         ),
         packages=find_packages(where="third_party/DeepGEMM"),
         package_dir={"": "third_party/DeepGEMM"},