[6/N] torch.compile rollout to users (#10437)

Signed-off-by: youkaichao <youkaichao@gmail.com>

vllm/envs.py

@@ -67,8 +67,6 @@ if TYPE_CHECKING:
     VLLM_USE_TRITON_AWQ: bool = False
     VLLM_ALLOW_RUNTIME_LORA_UPDATING: bool = False
     VLLM_SKIP_P2P_CHECK: bool = False
-    VLLM_TORCH_COMPILE_LEVEL: int = 0
-    VLLM_TORCH_COMPILE_CONFIG: Optional[str] = None
     VLLM_DISABLED_KERNELS: List[str] = []
     VLLM_USE_V1: bool = False
     VLLM_ENABLE_V1_MULTIPROCESSING: bool = False
@@ -209,12 +207,6 @@ environment_variables: Dict[str, Callable[[], Any]] = {
     "VLLM_TEST_DYNAMO_FULLGRAPH_CAPTURE":
     lambda: bool(
         os.environ.get("VLLM_TEST_DYNAMO_FULLGRAPH_CAPTURE", "1") != "0"),
-    "VLLM_TORCH_COMPILE_LEVEL":
-    lambda: int(os.environ.get("VLLM_TORCH_COMPILE_LEVEL", "0")),
-
-    # Path to the config file for torch compile
-    "VLLM_TORCH_COMPILE_CONFIG":
-    lambda: os.environ.get("VLLM_TORCH_COMPILE_CONFIG", None),
 
     # local rank of the process in the distributed setting, used to determine
     # the GPU device id