[Frontend] Refactor ServingTokenization entrypoint. (#46022)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
wang.yuqi
2026-06-22 06:27:58 +00:00
committed by GitHub
parent 31124749d1
commit 1eb2cc961e
15 changed files with 322 additions and 302 deletions
@@ -15,7 +15,7 @@ from vllm.entrypoints.serve.tokenize.protocol import (
TokenizeChatRequest,
TokenizeCompletionRequest,
)
from vllm.entrypoints.serve.tokenize.serving import OpenAIServingTokenization
from vllm.entrypoints.serve.tokenize.serving import ServingTokenization
from vllm.v1.engine.async_llm import AsyncLLM
MODEL_NAME = "openai-community/gpt2"
@@ -58,7 +58,7 @@ class MockModelConfig:
return self.diff_sampling_param or {}
def _build_serving_tokenization(engine: AsyncLLM) -> OpenAIServingTokenization:
def _build_serving_tokenization(engine: AsyncLLM) -> ServingTokenization:
models = OpenAIServingModels(
engine_client=engine,
base_model_paths=BASE_MODEL_PATHS,
@@ -71,8 +71,7 @@ def _build_serving_tokenization(engine: AsyncLLM) -> OpenAIServingTokenization:
chat_template=None,
chat_template_content_format="auto",
)
return OpenAIServingTokenization(
engine,
return ServingTokenization(
models,
openai_serving_render=serving_render,
request_logger=None,