[Frontend] Remove frontend pooling multi task support. (#37861)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
wang.yuqi
2026-04-21 12:27:44 +00:00
committed by GitHub
co-authored by Cyrus Leung mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent 766cb65d00
commit d2e2e856ad
26 changed files with 260 additions and 273 deletions
+7 -1
View File
@@ -8,6 +8,7 @@ from vllm.engine.protocol import EngineClient
from vllm.entrypoints.openai.engine.protocol import UsageInfo
from vllm.logger import init_logger
from vllm.outputs import PoolingRequestOutput, ScoringRequestOutput
from vllm.tasks import SCORE_TYPE_MAP, SupportedTask
from vllm.v1.pool.late_interaction import (
build_late_interaction_doc_params,
build_late_interaction_query_params,
@@ -38,10 +39,15 @@ class ServingScores(PoolingServing):
self,
engine_client: EngineClient,
*args,
supported_tasks: tuple[SupportedTask, ...],
enable_flash_late_interaction: bool = True,
**kwargs,
):
self.io_processor_name: str = engine_client.model_config.score_type
pooling_task = engine_client.model_config.get_pooling_task(supported_tasks)
score_type = SCORE_TYPE_MAP.get(pooling_task, None) # type: ignore[arg-type]
assert score_type is not None
self.io_processor_name: str = score_type
self.enable_flash_late_interaction = (
self.io_processor_name == "late-interaction"
and enable_flash_late_interaction