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

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

examples/offline_inference/logits_processor/custom.py

@@ -33,8 +33,6 @@ Output:    ' in the hands of the people.\n\nThe future of AI is in the'
 ------------------------------------------------------------
 """
 
-from typing import Optional
-
 import torch
 
 from vllm import LLM, SamplingParams
@@ -58,7 +56,7 @@ class DummyLogitsProcessor(LogitsProcessor):
     def is_argmax_invariant(self) -> bool:
         return False
 
-    def update_state(self, batch_update: Optional[BatchUpdate]):
+    def update_state(self, batch_update: BatchUpdate | None):
         process_dict_updates(
             self.req_info,
             batch_update,

examples/offline_inference/logits_processor/custom_req.py

@@ -39,7 +39,7 @@ Output:    ' in the hands of the people.\n\nThe future of AI is in the'
 ------------------------------------------------------------
 """
 
-from typing import Any, Optional
+from typing import Any
 
 import torch
 
@@ -82,7 +82,7 @@ class WrappedPerReqLogitsProcessor(AdapterLogitsProcessor):
     def new_req_logits_processor(
         self,
         params: SamplingParams,
-    ) -> Optional[RequestLogitsProcessor]:
+    ) -> RequestLogitsProcessor | None:
         """This method returns a new request-level logits processor, customized
         to the `target_token` value associated with a particular request.
 
@@ -96,7 +96,7 @@ class WrappedPerReqLogitsProcessor(AdapterLogitsProcessor):
         Returns:
           `Callable` request logits processor, or None
         """
-        target_token: Optional[Any] = params.extra_args and params.extra_args.get(
+        target_token: Any | None = params.extra_args and params.extra_args.get(
             "target_token"
         )
         if target_token is None:

examples/offline_inference/logits_processor/custom_req_init.py

@@ -41,8 +41,6 @@ which indicates that the logits processor is running. However, on a non-"cuda"
 device, the first and third requests would not repeat the same token.
 """
 
-from typing import Optional
-
 import torch
 
 from vllm import LLM, SamplingParams
@@ -91,7 +89,7 @@ class WrappedPerReqLogitsProcessor(AdapterLogitsProcessor):
     def new_req_logits_processor(
         self,
         params: SamplingParams,
-    ) -> Optional[RequestLogitsProcessor]:
+    ) -> RequestLogitsProcessor | None:
         """This method returns a new request-level logits processor, customized
         to the `target_token` value associated with a particular request.