rename tokenize serving api request id prefix to tokenize (#32328)

Signed-off-by: Andy Xie <andy.xning@gmail.com>

vllm/entrypoints/serve/tokenize/protocol.py

@@ -92,11 +92,11 @@ class TokenizeChatRequest(OpenAIBaseModel):
     )
     mm_processor_kwargs: dict[str, Any] | None = Field(
         default=None,
-        description=("Additional kwargs to pass to the HF processor."),
+        description="Additional kwargs to pass to the HF processor.",
     )
     tools: list[ChatCompletionToolsParam] | None = Field(
         default=None,
-        description=("A list of tools the model may call."),
+        description="A list of tools the model may call.",
     )
 
     @model_validator(mode="before")

vllm/entrypoints/serve/tokenize/serving.py

@@ -62,7 +62,7 @@ class OpenAIServingTokenization(OpenAIServing):
         if error_check_ret is not None:
             return error_check_ret
 
-        request_id = f"tokn-{self._base_request_id(raw_request)}"
+        request_id = f"tokenize-{self._base_request_id(raw_request)}"
 
         try:
             lora_request = self._maybe_get_adapters(request)
@@ -134,7 +134,7 @@ class OpenAIServingTokenization(OpenAIServing):
         if error_check_ret is not None:
             return error_check_ret
 
-        request_id = f"tokn-{self._base_request_id(raw_request)}"
+        request_id = f"tokenize-{self._base_request_id(raw_request)}"
 
         lora_request = self._maybe_get_adapters(request)