[Refactor] [1/N] to simplify the vLLM serving architecture

Signed-off-by: chaunceyjiang <[email protected]>

Author: chaunceyjiang

vllm/entrypoints/openai/api_server.py

@@ -82,7 +82,7 @@
 from vllm.entrypoints.serve.elastic_ep.middleware import (
     ScalingMiddleware,
 )
-from vllm.entrypoints.serve.tokenize.protocol import OpenAIServingTokenization
+from vllm.entrypoints.serve.tokenize.serving import OpenAIServingTokenization
 from vllm.entrypoints.tool_server import DemoToolServer, MCPToolServer, ToolServer
 from vllm.entrypoints.utils import (
     cli_env_setup,

vllm/entrypoints/serve/disagg/api_router.py

@@ -21,7 +21,7 @@
 from vllm.entrypoints.serve.disagg.serving import (
     ServingTokens,
 )
-from vllm.entrypoints.serve.tokenize.protocol import OpenAIServingTokenization
+from vllm.entrypoints.serve.tokenize.serving import OpenAIServingTokenization
 from vllm.entrypoints.utils import (
     load_aware_call,
     with_cancellation,

vllm/entrypoints/serve/tokenize/api_router.py

@@ -17,7 +17,7 @@
     TokenizeRequest,
     TokenizeResponse,
 )
-from vllm.entrypoints.serve.tokenize.protocol import OpenAIServingTokenization
+from vllm.entrypoints.serve.tokenize.serving import OpenAIServingTokenization
 from vllm.entrypoints.utils import (
     with_cancellation,
 )