[Frontend] Resettle generative scoring entrypoint. (#44153)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>

.buildkite/test-amd.yaml

@@ -1275,10 +1275,12 @@ steps:
   - vllm/
   - tests/entrypoints/openai
   - tests/entrypoints/test_chat_utils
+  - tests/entrypoints/generate
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
   - pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
   - pytest -v -s entrypoints/test_chat_utils.py
+  - pytest -v -s entrypoints/generate
 
 - label: Entrypoints Integration (API Server openai - Part 3) # TBD
   timeout_in_minutes: 180
@@ -1368,7 +1370,7 @@ steps:
   - vllm/platforms/rocm.py
   commands:
   - pytest -v -s entrypoints/openai/tool_parsers
-  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/rpc --ignore=entrypoints/sleep --ignore=entrypoints/serve/instrumentator --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling
+  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/rpc --ignore=entrypoints/sleep --ignore=entrypoints/serve/instrumentator --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling  --ignore=entrypoints/speech_to_text --ignore=tests/entrypoints/generate
 
 - label: OpenAI API correctness # TBD
   timeout_in_minutes: 180
@@ -2782,10 +2784,12 @@ steps:
   - vllm/
   - tests/entrypoints/openai
   - tests/entrypoints/test_chat_utils
+  - tests/entrypoints/generate
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
   - pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
   - pytest -v -s entrypoints/test_chat_utils.py
+  - pytest -v -s entrypoints/generate
 
 - label: Entrypoints Integration (API Server openai - Part 3) # TBD
   timeout_in_minutes: 180

.buildkite/test_areas/entrypoints.yaml

@@ -11,7 +11,7 @@ steps:
   - tests/entrypoints/
   commands:
   - pytest -v -s entrypoints/openai/tool_parsers
-  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/rpc --ignore=entrypoints/sleep --ignore=entrypoints/serve/instrumentator --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling --ignore=entrypoints/speech_to_text
+  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/rpc --ignore=entrypoints/sleep --ignore=entrypoints/serve/instrumentator --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling --ignore=entrypoints/speech_to_text --ignore=tests/entrypoints/generate
 
 - label: Entrypoints Integration (LLM)
   key: entrypoints-integration-llm
@@ -60,9 +60,11 @@ steps:
   - vllm/
   - tests/entrypoints/openai
   - tests/entrypoints/test_chat_utils
+  - tests/entrypoints/generate
   commands:
   - pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
   - pytest -v -s entrypoints/test_chat_utils.py
+  - pytest -v -s entrypoints/generate
   mirror:
     amd:
       device: mi325_1

tests/entrypoints/generate/generative_scoring/test_generative_scoring.py

@@ -18,13 +18,13 @@ from unittest.mock import MagicMock
 import pytest
 
 from vllm.config.multimodal import MultiModalConfig
-from vllm.entrypoints.openai.engine.protocol import ErrorResponse
-from vllm.entrypoints.openai.generative_scoring.serving import (
+from vllm.entrypoints.generate.generative_scoring.serving import (
     GenerativeScoringItemResult,
     GenerativeScoringRequest,
     GenerativeScoringResponse,
-    OpenAIServingGenerativeScoring,
+    ServingGenerativeScoring,
 )
+from vllm.entrypoints.openai.engine.protocol import ErrorResponse
 from vllm.entrypoints.openai.models.protocol import BaseModelPath
 from vllm.entrypoints.openai.models.serving import OpenAIServingModels
 from vllm.logprobs import Logprob
@@ -86,13 +86,13 @@ def _create_mock_engine():
     return mock_engine
 
 
-def _create_serving(mock_engine) -> OpenAIServingGenerativeScoring:
-    """Create an OpenAIServingGenerativeScoring instance with mocks."""
+def _create_serving(mock_engine) -> ServingGenerativeScoring:
+    """Create an ServingGenerativeScoring instance with mocks."""
     models = OpenAIServingModels(
         engine_client=mock_engine,
         base_model_paths=BASE_MODEL_PATHS,
     )
-    return OpenAIServingGenerativeScoring(mock_engine, models, request_logger=None)
+    return ServingGenerativeScoring(mock_engine, models, request_logger=None)
 
 
 def _create_mock_request_output(logprobs_dict: dict[int, float]) -> RequestOutput:
@@ -186,7 +186,7 @@ class TestProbabilityComputation:
         self, label_logprobs, apply_softmax, should_sum_to_one
     ):
         """Test probability computation for softmax and true probability modes."""
-        serving = OpenAIServingGenerativeScoring.__new__(OpenAIServingGenerativeScoring)
+        serving = ServingGenerativeScoring.__new__(ServingGenerativeScoring)
         probs = serving._compute_probabilities(
             label_logprobs, apply_softmax=apply_softmax
         )
@@ -211,7 +211,7 @@ class TestProbabilityComputation:
 
     def test_score_formula(self):
         """Test the score formula: P(token[0]) / (P(token[0]) + P(token[1]))."""
-        serving = OpenAIServingGenerativeScoring.__new__(OpenAIServingGenerativeScoring)
+        serving = ServingGenerativeScoring.__new__(ServingGenerativeScoring)
 
         # With logprobs -0.5 and -2.0, softmax gives higher prob to first token
         logprobs = {9454: -0.5, 2753: -2.0}

tests/entrypoints/generate/generative_scoring/test_generative_scoring_e2e.py

@@ -8,7 +8,7 @@ Tests verify the full HTTP request/response flow using RemoteOpenAIServer.
 import pytest
 import requests
 
-from ....utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
 
 MODEL_NAME = "Qwen/Qwen3-0.6B"
 

vllm/entrypoints/generate/api_router.py

@@ -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,
+    )

vllm/entrypoints/generate/generative_scoring/api_router.py

@@ -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,
-    )

vllm/entrypoints/generate/generative_scoring/serving.py

@@ -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

vllm/entrypoints/openai/api_server.py

@@ -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
 

vllm/entrypoints/sagemaker/api_router.py

@@ -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