[Frontend] Move engine/protocol.py out openai folder (#54492)

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>
This commit is contained in:
wang.yuqi
2026-08-31 10:13:50 +00:00
committed by GitHub
co-authored by Cyrus Leung
parent d8de4ae322
commit eeb549a74d
194 changed files with 550 additions and 585 deletions
@@ -16,14 +16,13 @@ from transformers import PreTrainedTokenizerBase
import vllm.envs as envs
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.generate.base.serving import GenerateBaseServing
from vllm.entrypoints.openai.engine.protocol import (
from vllm.entrypoints.generate.base.protocol import (
DeltaMessage,
ErrorResponse,
RequestResponseMetadata,
UsageInfo,
)
from vllm.entrypoints.generate.base.serving import GenerateBaseServing
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.serve.engine.protocol import ErrorResponse, UsageInfo
from vllm.entrypoints.serve.engine.typing import SpeechToTextRequest
from vllm.entrypoints.serve.utils.api_utils import get_max_tokens
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
@@ -13,7 +13,7 @@ from fastapi import WebSocket
from starlette.websockets import WebSocketDisconnect
from vllm import envs
from vllm.entrypoints.openai.engine.protocol import ErrorResponse, UsageInfo
from vllm.entrypoints.serve.engine.protocol import ErrorResponse, UsageInfo
from vllm.entrypoints.serve.exception_handling.utils import sanitize_message
from vllm.exceptions import VLLMValidationError
from vllm.logger import init_logger
@@ -6,10 +6,7 @@ from typing import Literal
from pydantic import Field
from vllm.entrypoints.openai.engine.protocol import (
OpenAIBaseModel,
UsageInfo,
)
from vllm.entrypoints.serve.engine.protocol import OpenAIBaseModel, UsageInfo
from vllm.utils import random_uuid
# Client -> Server Events
@@ -8,7 +8,6 @@ from typing import Annotated
from fastapi import APIRouter, Form, Request
from fastapi.responses import JSONResponse, StreamingResponse
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.serve.utils.api_utils import (
load_aware_call,
with_cancellation,
@@ -16,6 +15,7 @@ from vllm.entrypoints.serve.utils.api_utils import (
from vllm.entrypoints.speech_to_text.base.utils import read_upload_with_limit
from vllm.logger import init_logger
from ...serve.engine.protocol import ErrorResponse
from .protocol import TranscriptionRequest, TranscriptionResponseVariant
from .serving import OpenAIServingTranscription
@@ -13,11 +13,8 @@ from pydantic import (
)
from vllm.config.speech_to_text import SpeechToTextParams
from vllm.entrypoints.openai.engine.protocol import (
DeltaMessage,
OpenAIBaseModel,
UsageInfo,
)
from vllm.entrypoints.generate.base.protocol import DeltaMessage
from vllm.entrypoints.serve.engine.protocol import OpenAIBaseModel, UsageInfo
from vllm.exceptions import VLLMValidationError
from vllm.logger import init_logger
from vllm.sampling_params import (
@@ -5,15 +5,13 @@ from collections.abc import AsyncGenerator
from fastapi import Request
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
RequestResponseMetadata,
)
from vllm.entrypoints.generate.base.protocol import RequestResponseMetadata
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
from vllm.logger import init_logger
from vllm.outputs import RequestOutput
from ...serve.engine.protocol import ErrorResponse
from ..base.serving import SpeechToTextBaseServing
from .protocol import (
TranscriptionRequest,
@@ -8,7 +8,7 @@ from typing import Annotated
from fastapi import APIRouter, Form, Request
from fastapi.responses import JSONResponse, StreamingResponse
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
from vllm.entrypoints.serve.utils.api_utils import (
load_aware_call,
with_cancellation,
@@ -12,11 +12,8 @@ from pydantic import (
)
from vllm.config.speech_to_text import SpeechToTextParams
from vllm.entrypoints.openai.engine.protocol import (
DeltaMessage,
OpenAIBaseModel,
UsageInfo,
)
from vllm.entrypoints.generate.base.protocol import DeltaMessage
from vllm.entrypoints.serve.engine.protocol import OpenAIBaseModel, UsageInfo
from vllm.exceptions import VLLMValidationError
from vllm.logger import init_logger
from vllm.sampling_params import (
@@ -5,11 +5,9 @@ from collections.abc import AsyncGenerator
from fastapi import Request
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
RequestResponseMetadata,
)
from vllm.entrypoints.generate.base.protocol import RequestResponseMetadata
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
from vllm.logger import init_logger
from vllm.outputs import RequestOutput