[torch.compile] fast inductor (#11108)

Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

vllm/envs.py

@@ -71,6 +71,7 @@ if TYPE_CHECKING:
     VLLM_USE_V1: bool = False
     VLLM_ENABLE_V1_MULTIPROCESSING: bool = True
     VLLM_LOG_BATCHSIZE_INTERVAL: float = -1
+    VLLM_DISABLE_COMPILE_CACHE: bool = False
 
 
 def get_default_cache_root():
@@ -463,6 +464,8 @@ environment_variables: Dict[str, Callable[[], Any]] = {
     lambda: bool(int(os.getenv("VLLM_ENABLE_V1_MULTIPROCESSING", "1"))),
     "VLLM_LOG_BATCHSIZE_INTERVAL":
     lambda: float(os.getenv("VLLM_LOG_BATCHSIZE_INTERVAL", "-1")),
+    "VLLM_DISABLE_COMPILE_CACHE":
+    lambda: bool(int(os.getenv("VLLM_DISABLE_COMPILE_CACHE", "0"))),
 }
 
 # end-env-vars-definition