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

[Frontend][1/n] Make pooling entrypoints request schema consensus | CompletionRequest (#32395)

Browse Source 
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
wang.yuqi
2026-01-16 14:17:04 +08:00
committed by GitHub
parent 73f635a75f
commit 4ae77dfd42
22 changed files with 635 additions and 600 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
vllm/entrypoints/openai/api_server.py
View File

@@ -54,10 +54,6 @@ from vllm.entrypoints.openai.translations.serving import (
OpenAIServingTranscription,
OpenAIServingTranslation,
)
from vllm.entrypoints.pooling.classify.serving import ServingClassification
from vllm.entrypoints.pooling.embed.serving import OpenAIServingEmbedding
from vllm.entrypoints.pooling.pooling.serving import OpenAIServingPooling
from vllm.entrypoints.pooling.score.serving import ServingScores
from vllm.entrypoints.serve.disagg.serving import ServingTokens
from vllm.entrypoints.serve.elastic_ep.middleware import (
ScalingMiddleware,
@@ -73,7 +69,6 @@ from vllm.entrypoints.utils import (
from vllm.exceptions import VLLMValidationError
from vllm.logger import init_logger
from vllm.reasoning import ReasoningParserManager
from vllm.tasks import POOLING_TASKS
from vllm.tool_parsers import ToolParserManager
from vllm.usage.usage_lib import UsageContext
from vllm.utils.argparse_utils import FlexibleArgumentParser
@@ -761,59 +756,6 @@ async def init_app_state(
if "generate" in supported_tasks
else None
)
state.openai_serving_pooling = (
(
OpenAIServingPooling(
engine_client,
state.openai_serving_models,
supported_tasks=supported_tasks,
request_logger=request_logger,
chat_template=resolved_chat_template,
chat_template_content_format=args.chat_template_content_format,
trust_request_chat_template=args.trust_request_chat_template,
log_error_stack=args.log_error_stack,
)
)
if any(task in POOLING_TASKS for task in supported_tasks)
else None
)
state.openai_serving_embedding = (
OpenAIServingEmbedding(
engine_client,
state.openai_serving_models,
request_logger=request_logger,
chat_template=resolved_chat_template,
chat_template_content_format=args.chat_template_content_format,
trust_request_chat_template=args.trust_request_chat_template,
log_error_stack=args.log_error_stack,
)
if "embed" in supported_tasks
else None
)
state.openai_serving_classification = (
ServingClassification(
engine_client,
state.openai_serving_models,
request_logger=request_logger,
chat_template=resolved_chat_template,
chat_template_content_format=args.chat_template_content_format,
trust_request_chat_template=args.trust_request_chat_template,
log_error_stack=args.log_error_stack,
)
if "classify" in supported_tasks
else None
)
state.openai_serving_scores = (
ServingScores(
engine_client,
state.openai_serving_models,
request_logger=request_logger,
score_template=resolved_chat_template,
log_error_stack=args.log_error_stack,
)
if ("embed" in supported_tasks or "score" in supported_tasks)
else None
)
state.openai_serving_tokenization = OpenAIServingTokenization(
engine_client,
state.openai_serving_models,
@@ -878,6 +820,10 @@ async def init_app_state(
else None
)
from vllm.entrypoints.pooling import init_pooling_state
await init_pooling_state(engine_client, state, args)
state.enable_server_load_tracking = args.enable_server_load_tracking
state.server_load_metrics = 0