biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Model] Deprecate the score task (this will not affect users). (#37537)

Browse Source 
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
wang.yuqi
2026-03-20 16:07:56 +08:00
committed by GitHub
parent dcee9be95a
commit ed359c497a
22 changed files with 184 additions and 163 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
vllm/entrypoints/openai/api_server.py
View File

@@ -22,7 +22,7 @@ from fastapi.middleware.cors import CORSMiddleware
from starlette.datastructures import State
import vllm.envs as envs
from vllm.config import VllmConfig
from vllm.config import ModelConfig, VllmConfig
from vllm.engine.arg_utils import AsyncEngineArgs
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.chat_utils import load_chat_template
@@ -155,7 +155,9 @@ async def build_async_engine_client_from_engine_args(
def build_app(
args: Namespace, supported_tasks: tuple["SupportedTask", ...] | None = None
args: Namespace,
supported_tasks: tuple["SupportedTask", ...] | None = None,
model_config: ModelConfig | None = None,
) -> FastAPI:
if supported_tasks is None:
warnings.warn(
@@ -191,7 +193,7 @@ def build_app(
attach_router as register_sagemaker_api_router,
)
register_sagemaker_api_router(app, supported_tasks)
register_sagemaker_api_router(app, supported_tasks, model_config)
if "generate" in supported_tasks:
from vllm.entrypoints.openai.generate.api_router import (
@@ -242,7 +244,7 @@ def build_app(
if any(task in POOLING_TASKS for task in supported_tasks):
from vllm.entrypoints.pooling import register_pooling_api_routers
register_pooling_api_routers(app, supported_tasks)
register_pooling_api_routers(app, supported_tasks, model_config)
app.root_path = args.root_path
app.add_middleware(
@@ -583,8 +585,10 @@ async def build_and_serve(
uvicorn_kwargs["log_config"] = log_config
supported_tasks = await engine_client.get_supported_tasks()
model_config = engine_client.model_config
logger.info("Supported tasks: %s", supported_tasks)
app = build_app(args, supported_tasks)
app = build_app(args, supported_tasks, model_config)
await init_app_state(engine_client, app.state, args, supported_tasks)
logger.info("Starting vLLM server on %s", listen_address)