[Bugfix] Fix generative scoring body cancellation (#57729)

Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

Taneem Ibrahim committed Sep 25, 2026 at 10:01 UTC 50f78084da2af4c79f54aa19f09972e2ec5d1049
1 file changed +5 -9
vllm/entrypoints/generate/generative_scoring/api_router.py
+5 -9
@@ -6,6 +6,7 @@ from fastapi import APIRouter, Depends, FastAPI, Request
6 from fastapi.responses import JSONResponse
7
8 from vllm.entrypoints.generate.generative_scoring.serving import (
9 + GenerativeScoringRequest,
10 GenerativeScoringResponse,
11 ServingGenerativeScoring,
12 )
@@ -36,21 +37,16 @@ def generative_scoring(request: Request) -> ServingGenerativeScoring | None:
37 )
38 @with_cancellation
39 @load_aware_call
39 -async def create_generative_scoring(raw_request: Request):
40 +async def create_generative_scoring(
41 + request: GenerativeScoringRequest, raw_request: Request
42 +):
43 handler = generative_scoring(raw_request)
44 if handler is None:
45 raise NotImplementedError(
46 "The model does not support the Generative Scoring API"
47 )
48
46 - raw_body = await raw_request.json()
47 -
48 - from vllm.entrypoints.generate.generative_scoring.serving import (
49 - GenerativeScoringRequest,
50 - )
51 -
52 - gen_request = GenerativeScoringRequest(**raw_body)
53 - result = await handler.create_generative_scoring(gen_request, raw_request)
49 + result = await handler.create_generative_scoring(request, raw_request)
50
51 if isinstance(result, ErrorResponse):
52 return JSONResponse(content=result.model_dump(), status_code=result.error.code)