[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
@@ -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}
@@ -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"