[Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
Chauncey
2026-01-13 13:01:39 +00:00
committed by GitHub
parent a5bbbd2f24
commit fefce49807
128 changed files with 1221 additions and 1008 deletions
@@ -6,7 +6,7 @@ from fastapi import APIRouter, Depends, HTTPException, Request
from starlette.responses import JSONResponse
from typing_extensions import assert_never
from vllm.entrypoints.openai.protocol import ErrorResponse
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.openai.utils import validate_json_request
from vllm.entrypoints.pooling.classify.protocol import (
ClassificationRequest,
@@ -11,7 +11,7 @@ from pydantic import (
from vllm import PoolingParams
from vllm.config.pooler import get_use_activation
from vllm.entrypoints.chat_utils import ChatCompletionMessageParam
from vllm.entrypoints.openai.protocol import OpenAIBaseModel, UsageInfo
from vllm.entrypoints.openai.engine.protocol import OpenAIBaseModel, UsageInfo
from vllm.utils import random_uuid
+4 -2
View File
@@ -11,12 +11,14 @@ from fastapi import Request
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.chat_utils import ChatTemplateContentFormatOption
from vllm.entrypoints.logger import RequestLogger
from vllm.entrypoints.openai.protocol import (
from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionRequest,
)
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
UsageInfo,
)
from vllm.entrypoints.openai.serving_engine import (
from vllm.entrypoints.openai.engine.serving import (
ClassificationServeContext,
OpenAIServing,
ServeContext,
+1 -1
View File
@@ -6,7 +6,7 @@ from fastapi import APIRouter, Depends, HTTPException, Request
from fastapi.responses import JSONResponse, StreamingResponse
from typing_extensions import assert_never
from vllm.entrypoints.openai.protocol import ErrorResponse
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.openai.utils import validate_json_request
from vllm.entrypoints.pooling.embed.protocol import (
EmbeddingBytesResponse,
+1 -1
View File
@@ -10,7 +10,7 @@ from pydantic import (
from vllm import PoolingParams
from vllm.entrypoints.chat_utils import ChatCompletionMessageParam
from vllm.entrypoints.openai.protocol import OpenAIBaseModel, UsageInfo
from vllm.entrypoints.openai.engine.protocol import OpenAIBaseModel, UsageInfo
from vllm.utils import random_uuid
from vllm.utils.serial_utils import EmbedDType, EncodingFormat, Endianness
+2 -2
View File
@@ -12,11 +12,11 @@ from typing_extensions import assert_never, override
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.chat_utils import ChatTemplateContentFormatOption
from vllm.entrypoints.logger import RequestLogger
from vllm.entrypoints.openai.protocol import (
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
UsageInfo,
)
from vllm.entrypoints.openai.serving_engine import (
from vllm.entrypoints.openai.engine.serving import (
EmbeddingServeContext,
OpenAIServing,
ServeContext,
@@ -6,7 +6,7 @@ from fastapi import APIRouter, Depends, HTTPException, Request
from fastapi.responses import JSONResponse, StreamingResponse
from typing_extensions import assert_never
from vllm.entrypoints.openai.protocol import ErrorResponse
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.openai.utils import validate_json_request
from vllm.entrypoints.pooling.pooling.protocol import (
IOProcessorResponse,
+1 -1
View File
@@ -9,7 +9,7 @@ from pydantic import (
from vllm import PoolingParams
from vllm.config.pooler import get_use_activation
from vllm.entrypoints.openai.protocol import OpenAIBaseModel, UsageInfo
from vllm.entrypoints.openai.engine.protocol import OpenAIBaseModel, UsageInfo
from vllm.entrypoints.pooling.embed.protocol import (
EmbeddingChatRequest,
EmbeddingCompletionRequest,
+2 -2
View File
@@ -14,11 +14,11 @@ from typing_extensions import assert_never
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.chat_utils import ChatTemplateContentFormatOption
from vllm.entrypoints.logger import RequestLogger
from vllm.entrypoints.openai.protocol import (
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
UsageInfo,
)
from vllm.entrypoints.openai.serving_engine import OpenAIServing
from vllm.entrypoints.openai.engine.serving import OpenAIServing
from vllm.entrypoints.openai.serving_models import OpenAIServingModels
from vllm.entrypoints.pooling.pooling.protocol import (
IOProcessorRequest,
+1 -1
View File
@@ -6,7 +6,7 @@ from fastapi import APIRouter, Depends, HTTPException, Request
from fastapi.responses import JSONResponse
from typing_extensions import assert_never
from vllm.entrypoints.openai.protocol import ErrorResponse
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.openai.utils import validate_json_request
from vllm.entrypoints.pooling.score.protocol import (
RerankRequest,
+1 -1
View File
@@ -10,7 +10,7 @@ from pydantic import (
from vllm import PoolingParams
from vllm.config.pooler import get_use_activation
from vllm.entrypoints.openai.protocol import OpenAIBaseModel, UsageInfo
from vllm.entrypoints.openai.engine.protocol import OpenAIBaseModel, UsageInfo
from vllm.entrypoints.score_utils import ScoreContentPartParam, ScoreMultiModalParam
from vllm.utils import random_uuid
+2 -2
View File
@@ -9,11 +9,11 @@ from fastapi import Request
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.logger import RequestLogger
from vllm.entrypoints.openai.protocol import (
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
UsageInfo,
)
from vllm.entrypoints.openai.serving_engine import OpenAIServing
from vllm.entrypoints.openai.engine.serving import OpenAIServing
from vllm.entrypoints.openai.serving_models import OpenAIServingModels
from vllm.entrypoints.pooling.score.protocol import (
RerankDocument,