[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:
@@ -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,
|
||||
|
||||
@@ -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
|
||||
|
||||
|
||||
@@ -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,
|
||||
|
||||
Reference in New Issue
Block a user