[Frontend] Add cache salt support to generative scoring (#60841)

Signed-off-by: Taewoong Kim <ktw2172@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
Taewoong Kim
2026-10-09 16:07:50 +00:00
committed by GitHub
co-authored by Cyrus Leung
parent 90ba2f34b5
commit 75e3b17c05
5 changed files with 68 additions and 9 deletions
@@ -13,6 +13,9 @@ request models whose before-validators were missing the same guard.
import pytest
from pydantic import ValidationError
from vllm.entrypoints.generate.generative_scoring.serving import (
GenerativeScoringRequest,
)
from vllm.entrypoints.generate.structured_decisions.protocol import (
StructuredDecisionRequest,
)
@@ -31,6 +34,7 @@ from vllm.exceptions import VLLMValidationError
pytestmark = pytest.mark.skip_global_cleanup
REQUEST_MODELS = [
GenerativeScoringRequest,
CompletionRequest,
ResponsesRequest,
EmbeddingChatRequest,
@@ -77,6 +81,14 @@ def test_tokenize_chat_request_still_validates_dict_bodies():
CACHE_SALT_MODELS = [
(
GenerativeScoringRequest,
{
"query": "Is this city the capital of France?",
"items": ["Paris"],
"label_token_ids": [9454, 2753],
},
),
(
StructuredDecisionRequest,
{