[Frontend] Explain disabled scale-out endpoints with opt-in hints (#61042)

Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
This commit is contained in:
aoshen02
2026-10-11 08:58:07 +00:00
committed by GitHub
co-authored by OpenAI Codex
parent fcae5c9887
commit 1789f09588
5 changed files with 117 additions and 24 deletions
+34 -7
View File
@@ -1,11 +1,17 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from argparse import Namespace
from http import HTTPStatus
from typing import TYPE_CHECKING
from fastapi import FastAPI
from fastapi.responses import JSONResponse
from fastapi.routing import APIRoute
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.serve.exception_handling.error_response import (
create_error_response,
)
from vllm.logger import init_logger
from vllm.tasks import SupportedTask
@@ -66,6 +72,9 @@ def register_scale_out_api_routers(
app: FastAPI,
supported_tasks: tuple["SupportedTask", ...],
):
from .derender.api_router import router as derender_render
from .render.api_router import router as render_render
args = getattr(app.state, "args", None)
# `vllm launch render` and `vllm serve --tokens-only` are dedicated to
# serving these endpoints, so they always register them regardless of
@@ -73,17 +82,35 @@ def register_scale_out_api_routers(
dedicated_mode = "render" in supported_tasks or getattr(args, "tokens_only", False)
enabled = dedicated_mode or getattr(args, "enable_scale_out", False)
if not enabled:
logger.info(
"Scale-out endpoints are disabled. Set --enable-scale-out to enable them."
message = (
"Scale-out endpoints are disabled. Restart vllm serve with "
"--enable-scale-out to enable them."
)
logger.info(message)
async def disabled_scale_out() -> JSONResponse:
error = create_error_response(
message, "PermissionDeniedError", HTTPStatus.FORBIDDEN
)
return JSONResponse(error.model_dump(), status_code=HTTPStatus.FORBIDDEN)
from .token_in_token_out.api_router import router as token_router
for route in (
*render_render.routes,
*derender_render.routes,
*token_router.routes,
):
if isinstance(route, APIRoute):
app.add_api_route(
route.path,
disabled_scale_out,
methods=sorted(route.methods),
include_in_schema=False,
)
return
from .render.api_router import router as render_render
app.include_router(render_render)
from .derender.api_router import router as derender_render
app.include_router(derender_render)
if "generate" in supported_tasks: