[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:
@@ -5,7 +5,7 @@ from http import HTTPStatus
|
||||
from fastapi import APIRouter, Depends, Request
|
||||
from fastapi.responses import JSONResponse
|
||||
|
||||
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.serve.utils.api_utils import validate_json_request
|
||||
from vllm.logger import init_logger
|
||||
|
||||
|
||||
@@ -12,14 +12,11 @@ from vllm.entrypoints.openai.completion.protocol import (
|
||||
CompletionResponse,
|
||||
CompletionStreamResponse,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
ErrorResponse,
|
||||
UsageInfo,
|
||||
)
|
||||
from vllm.entrypoints.openai.models.serving import (
|
||||
OpenAIModelRegistry,
|
||||
OpenAIServingModels,
|
||||
)
|
||||
from vllm.entrypoints.serve.engine.protocol import ErrorResponse, UsageInfo
|
||||
from vllm.entrypoints.serve.engine.serving import BaseServing
|
||||
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
|
||||
from vllm.inputs import (
|
||||
|
||||
@@ -8,7 +8,7 @@ from fastapi.responses import JSONResponse
|
||||
from vllm.entrypoints.anthropic.protocol import AnthropicMessagesRequest
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.completion.protocol import CompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.serve.utils.api_utils import validate_json_request
|
||||
from vllm.logger import init_logger
|
||||
|
||||
|
||||
@@ -6,7 +6,6 @@ from vllm.entrypoints.anthropic.protocol import AnthropicMessagesRequest
|
||||
from vllm.entrypoints.anthropic.serving import AnthropicServingMessages
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.completion.protocol import CompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.openai.models.serving import (
|
||||
OpenAIModelRegistry,
|
||||
OpenAIServingModels,
|
||||
@@ -17,6 +16,7 @@ from vllm.entrypoints.scale_out.token_in_token_out.protocol import (
|
||||
MultiModalFeatures,
|
||||
PlaceholderRangeInfo,
|
||||
)
|
||||
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.serve.engine.serving import BaseServing
|
||||
from vllm.entrypoints.serve.utils.api_utils import get_max_tokens
|
||||
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
|
||||
|
||||
@@ -10,7 +10,6 @@ from fastapi import APIRouter, Depends, FastAPI, HTTPException, Request, Respons
|
||||
from fastapi.responses import JSONResponse, StreamingResponse
|
||||
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.serve.tokenize.serving import ServingTokenization
|
||||
from vllm.entrypoints.serve.utils.api_utils import (
|
||||
load_aware_call,
|
||||
@@ -19,6 +18,7 @@ from vllm.entrypoints.serve.utils.api_utils import (
|
||||
)
|
||||
from vllm.logger import init_logger
|
||||
|
||||
from ...serve.engine.protocol import ErrorResponse
|
||||
from .protocol import (
|
||||
GenerateRequest,
|
||||
GenerateResponse,
|
||||
|
||||
@@ -11,6 +11,7 @@ from pydantic import (
|
||||
)
|
||||
|
||||
from vllm.config import ModelConfig
|
||||
from vllm.entrypoints.generate.base.protocol import StreamOptions
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionLogProbs,
|
||||
ChatCompletionRequest,
|
||||
@@ -20,7 +21,7 @@ from vllm.entrypoints.openai.completion.protocol import (
|
||||
CompletionRequest,
|
||||
CompletionStreamResponse,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import StreamOptions, UsageInfo
|
||||
from vllm.entrypoints.serve.engine.protocol import UsageInfo
|
||||
from vllm.logprobs import Logprob
|
||||
from vllm.renderers import TokenizeParams
|
||||
from vllm.sampling_params import SamplingParams
|
||||
|
||||
@@ -12,6 +12,7 @@ from fastapi import Request
|
||||
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.chat_utils import AsyncMultiModalItemTracker
|
||||
from vllm.entrypoints.generate.base.protocol import RequestResponseMetadata
|
||||
from vllm.entrypoints.generate.base.serving import (
|
||||
GenerateBaseServing,
|
||||
clamp_prompt_logprobs,
|
||||
@@ -21,16 +22,15 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionLogProbs,
|
||||
ChatCompletionLogProbsContent,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
|
||||
from vllm.entrypoints.serve.engine.protocol import (
|
||||
ErrorResponse,
|
||||
GenerationError,
|
||||
PromptTokenUsageInfo,
|
||||
RequestResponseMetadata,
|
||||
UsageInfo,
|
||||
)
|
||||
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
|
||||
from vllm.entrypoints.serve.utils.api_utils import get_max_tokens, should_include_usage
|
||||
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
|
||||
from vllm.exceptions import GenerationError
|
||||
from vllm.inputs import EngineInput, TokensPrompt, mm_input
|
||||
from vllm.logger import init_logger
|
||||
from vllm.logprobs import Logprob
|
||||
|
||||
Reference in New Issue
Block a user