Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

vllm/usage/usage_lib.py

@@ -10,7 +10,7 @@ import time
 from enum import Enum
 from pathlib import Path
 from threading import Thread
-from typing import Any, Optional, Union
+from typing import Any
 from uuid import uuid4
 
 import cpuinfo
@@ -32,7 +32,7 @@ _USAGE_STATS_DO_NOT_TRACK_PATH = os.path.join(_config_home, "do_not_track")
 _USAGE_STATS_ENABLED = None
 _USAGE_STATS_SERVER = envs.VLLM_USAGE_STATS_SERVER
 
-_GLOBAL_RUNTIME_DATA = dict[str, Union[str, int, bool]]()
+_GLOBAL_RUNTIME_DATA = dict[str, str | int | bool]()
 
 _USAGE_ENV_VARS_TO_COLLECT = [
     "VLLM_USE_MODELSCOPE",
@@ -46,7 +46,7 @@ _USAGE_ENV_VARS_TO_COLLECT = [
 ]
 
 
-def set_runtime_usage_data(key: str, value: Union[str, int, bool]) -> None:
+def set_runtime_usage_data(key: str, value: str | int | bool) -> None:
     """Set global usage data that will be sent with every usage heartbeat."""
     _GLOBAL_RUNTIME_DATA[key] = value
 
@@ -131,33 +131,33 @@ class UsageMessage:
         self.uuid = str(uuid4())
 
         # Environment Information
-        self.provider: Optional[str] = None
-        self.num_cpu: Optional[int] = None
-        self.cpu_type: Optional[str] = None
-        self.cpu_family_model_stepping: Optional[str] = None
-        self.total_memory: Optional[int] = None
-        self.architecture: Optional[str] = None
-        self.platform: Optional[str] = None
-        self.cuda_runtime: Optional[str] = None
-        self.gpu_count: Optional[int] = None
-        self.gpu_type: Optional[str] = None
-        self.gpu_memory_per_device: Optional[int] = None
-        self.env_var_json: Optional[str] = None
+        self.provider: str | None = None
+        self.num_cpu: int | None = None
+        self.cpu_type: str | None = None
+        self.cpu_family_model_stepping: str | None = None
+        self.total_memory: int | None = None
+        self.architecture: str | None = None
+        self.platform: str | None = None
+        self.cuda_runtime: str | None = None
+        self.gpu_count: int | None = None
+        self.gpu_type: str | None = None
+        self.gpu_memory_per_device: int | None = None
+        self.env_var_json: str | None = None
 
         # vLLM Information
-        self.model_architecture: Optional[str] = None
-        self.vllm_version: Optional[str] = None
-        self.context: Optional[str] = None
+        self.model_architecture: str | None = None
+        self.vllm_version: str | None = None
+        self.context: str | None = None
 
         # Metadata
-        self.log_time: Optional[int] = None
-        self.source: Optional[str] = None
+        self.log_time: int | None = None
+        self.source: str | None = None
 
     def report_usage(
         self,
         model_architecture: str,
         usage_context: UsageContext,
-        extra_kvs: Optional[dict[str, Any]] = None,
+        extra_kvs: dict[str, Any] | None = None,
     ) -> None:
         t = Thread(
             target=self._report_usage_worker,