[Frontend] Frontend will only attach supported tasks corresponding entrypoints. (#33139)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
wang.yuqi
2026-01-27 12:15:43 +00:00
committed by GitHub
co-authored by Cyrus Leung
parent da8d0c441a
commit 76139d0801
10 changed files with 467 additions and 345 deletions
+31 -17
View File
@@ -11,40 +11,54 @@ if TYPE_CHECKING:
from starlette.datastructures import State
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.logger import RequestLogger
from vllm.tasks import SupportedTask
else:
RequestLogger = object
SupportedTask = object
def register_pooling_api_routers(app: FastAPI):
from vllm.entrypoints.pooling.classify.api_router import router as classify_router
from vllm.entrypoints.pooling.embed.api_router import router as embed_router
def register_pooling_api_routers(
app: FastAPI, supported_tasks: tuple["SupportedTask", ...]
):
from vllm.entrypoints.pooling.pooling.api_router import router as pooling_router
from vllm.entrypoints.pooling.score.api_router import router as score_router
app.include_router(classify_router)
app.include_router(embed_router)
app.include_router(score_router)
app.include_router(pooling_router)
if "classify" in supported_tasks:
from vllm.entrypoints.pooling.classify.api_router import (
router as classify_router,
)
async def init_pooling_state(
engine_client: "EngineClient", state: "State", args: "Namespace"
app.include_router(classify_router)
if "embed" in supported_tasks:
from vllm.entrypoints.pooling.embed.api_router import router as embed_router
app.include_router(embed_router)
if "score" in supported_tasks or "embed" in supported_tasks:
from vllm.entrypoints.pooling.score.api_router import router as score_router
app.include_router(score_router)
def init_pooling_state(
engine_client: "EngineClient",
state: "State",
args: "Namespace",
request_logger: RequestLogger | None,
supported_tasks: tuple["SupportedTask", ...],
):
from vllm.entrypoints.chat_utils import load_chat_template
from vllm.entrypoints.logger import RequestLogger
from vllm.entrypoints.pooling.classify.serving import ServingClassification
from vllm.entrypoints.pooling.embed.serving import OpenAIServingEmbedding
from vllm.entrypoints.pooling.pooling.serving import OpenAIServingPooling
from vllm.entrypoints.pooling.score.serving import ServingScores
from vllm.tasks import POOLING_TASKS
supported_tasks = await engine_client.get_supported_tasks()
resolved_chat_template = load_chat_template(args.chat_template)
if args.enable_log_requests:
request_logger = RequestLogger(max_log_len=args.max_log_len)
else:
request_logger = None
state.openai_serving_pooling = (
(
OpenAIServingPooling(