[Frontend][last/5] Improve pooling entrypoints | clean up. (#39675)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
wang.yuqi
2026-04-16 07:53:23 -07:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent 5e5afafa21
commit 4e8c3f1c19
29 changed files with 466 additions and 428 deletions
+14 -16
View File
@@ -220,6 +220,12 @@ 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,
@@ -242,17 +248,10 @@ def build_app(
register_realtime_api_router(app)
if any(task in POOLING_TASKS for task in supported_tasks):
from vllm.entrypoints.pooling import register_pooling_api_routers
from vllm.entrypoints.pooling.factories import register_pooling_api_routers
register_pooling_api_routers(app, supported_tasks, model_config)
if "generate" in supported_tasks:
from vllm.entrypoints.openai.generative_scoring.api_router import (
register_generative_scoring_api_router,
)
register_generative_scoring_api_router(app)
app.root_path = args.root_path
app.add_middleware(
CORSMiddleware,
@@ -401,6 +400,12 @@ async def init_app_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:
from vllm.entrypoints.openai.speech_to_text.api_router import (
init_transcription_state,
@@ -416,17 +421,10 @@ async def init_app_state(
init_realtime_state(engine_client, state, args, request_logger, supported_tasks)
if any(task in POOLING_TASKS for task in supported_tasks):
from vllm.entrypoints.pooling import init_pooling_state
from vllm.entrypoints.pooling.factories import init_pooling_state
init_pooling_state(engine_client, state, args, request_logger, supported_tasks)
if "generate" in 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)
state.enable_server_load_tracking = args.enable_server_load_tracking
state.server_load_metrics = 0