[Frontend] Resettle generative scoring entrypoint. (#44153)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
wang.yuqi
2026-06-01 07:54:59 +00:00
committed by GitHub
parent 1f6048abe5
commit 0910f7e0e1
13 changed files with 38 additions and 58 deletions
+2 -14
View File
@@ -196,7 +196,7 @@ def build_app(
register_sagemaker_api_router(app, supported_tasks, model_config)
if "generate" in supported_tasks:
from vllm.entrypoints.openai.generate.api_router import (
from vllm.entrypoints.generate.api_router import (
register_generate_api_routers,
)
@@ -220,12 +220,6 @@ def build_app(
elastic_ep_attach_router(app)
from vllm.entrypoints.openai.generative_scoring.api_router import (
register_generative_scoring_api_router,
)
register_generative_scoring_api_router(app)
if "generate" in supported_tasks or "render" in supported_tasks:
from vllm.entrypoints.serve.render.api_router import (
attach_router as attach_render_router,
@@ -402,18 +396,12 @@ async def init_app_state(
)
if "generate" in supported_tasks:
from vllm.entrypoints.openai.generate.api_router import init_generate_state
from vllm.entrypoints.generate.api_router import init_generate_state
await init_generate_state(
engine_client, state, args, request_logger, supported_tasks
)
from vllm.entrypoints.openai.generative_scoring.api_router import (
init_generative_scoring_state,
)
await init_generative_scoring_state(engine_client, state, args, request_logger)
if "transcription" in supported_tasks or "realtime" in supported_tasks:
from vllm.entrypoints.speech_to_text.factories import init_speech_to_text_state