[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
@@ -41,6 +41,10 @@ def register_generate_api_routers(app: FastAPI):
register_anthropic_api_router(app)
from .generative_scoring.api_router import register_generative_scoring_api_router
register_generative_scoring_api_router(app)
async def init_generate_state(
engine_client: "EngineClient",
@@ -185,3 +189,11 @@ async def init_generate_state(
if "generate" in supported_tasks
else None
)
from .generative_scoring.serving import ServingGenerativeScoring
state.serving_generative_scoring = ServingGenerativeScoring(
engine_client,
state.openai_serving_models,
request_logger=request_logger,
)
@@ -1,34 +1,25 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from http import HTTPStatus
from typing import TYPE_CHECKING
from fastapi import APIRouter, Depends, FastAPI, Request
from fastapi.responses import JSONResponse
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.openai.generative_scoring.serving import (
from vllm.entrypoints.generate.generative_scoring.serving import (
GenerativeScoringResponse,
OpenAIServingGenerativeScoring,
ServingGenerativeScoring,
)
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.openai.utils import validate_json_request
from vllm.entrypoints.utils import load_aware_call, with_cancellation
from vllm.logger import init_logger
if TYPE_CHECKING:
from argparse import Namespace
from starlette.datastructures import State
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.logger import RequestLogger
router = APIRouter()
logger = init_logger(__name__)
def generative_scoring(request: Request) -> OpenAIServingGenerativeScoring | None:
def generative_scoring(request: Request) -> ServingGenerativeScoring | None:
return request.app.state.serving_generative_scoring
@@ -51,7 +42,7 @@ async def create_generative_scoring(raw_request: Request):
raw_body = await raw_request.json()
from vllm.entrypoints.openai.generative_scoring.serving import (
from vllm.entrypoints.generate.generative_scoring.serving import (
GenerativeScoringRequest,
)
@@ -68,20 +59,3 @@ async def create_generative_scoring(raw_request: Request):
def register_generative_scoring_api_router(app: FastAPI):
app.include_router(router)
async def init_generative_scoring_state(
engine_client: "EngineClient",
state: "State",
args: "Namespace",
request_logger: "RequestLogger | None",
):
from vllm.entrypoints.openai.generative_scoring.serving import (
OpenAIServingGenerativeScoring,
)
state.serving_generative_scoring = OpenAIServingGenerativeScoring(
engine_client,
state.openai_serving_models,
request_logger=request_logger,
)
@@ -142,7 +142,7 @@ class GenerativeScoringResponse(OpenAIBaseModel):
# ============================================================================
class OpenAIServingGenerativeScoring(OpenAIServing):
class ServingGenerativeScoring(OpenAIServing):
"""Serving class for generative scoring computation.
This class handles computing the probability of specified token IDs
+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
+1 -1
View File
@@ -11,9 +11,9 @@ from fastapi import APIRouter, Depends, FastAPI, HTTPException, Request
from fastapi.responses import JSONResponse, Response
from vllm.config import ModelConfig
from vllm.entrypoints.generate.factories import get_generate_invocation_types
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.openai.engine.serving import OpenAIServing
from vllm.entrypoints.openai.generate.factories import get_generate_invocation_types
from vllm.entrypoints.openai.utils import validate_json_request
from vllm.entrypoints.pooling.base.serving import PoolingServingBase
from vllm.entrypoints.pooling.factories import get_pooling_invocation_types