biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Generative Scoring (#34539)

Browse Source 
Signed-off-by: Vedant Jhaveri <vjhaveri@linkedin.com>
Co-authored-by: Vedant Jhaveri <vjhaveri@linkedin.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
Vedant V Jhaveri
2026-03-31 16:02:11 -07:00
committed by GitHub
parent 36f1dc19ae
commit 2e56975657
13 changed files with 1265 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
vllm/entrypoints/openai/api_server.py
View File

@@ -246,6 +246,13 @@ def build_app(
register_pooling_api_routers(app, supported_tasks, model_config)
if "generate" in supported_tasks:
from vllm.entrypoints.openai.generative_scoring.api_router import (
register_generative_scoring_api_router,
)
register_generative_scoring_api_router(app)
app.root_path = args.root_path
app.add_middleware(
CORSMiddleware,
@@ -413,6 +420,13 @@ async def init_app_state(
init_pooling_state(engine_client, state, args, request_logger, supported_tasks)
if "generate" in 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)
state.enable_server_load_tracking = args.enable_server_load_tracking
state.server_load_metrics = 0