[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
@@ -12,8 +12,8 @@ from vllm.entrypoints.openai.completion.protocol import (
CompletionResponse,
)
from vllm.entrypoints.openai.completion.serving import OpenAIServingCompletion
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.openai.sse_keep_alive import with_sse_keep_alive
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
from vllm.entrypoints.serve.utils.api_utils import (
load_aware_call,
validate_json_request,
@@ -10,17 +10,16 @@ from pydantic import Field, model_validator
import vllm.envs as envs
from vllm.config import ModelConfig
from vllm.entrypoints.openai.engine.protocol import (
from vllm.entrypoints.generate.base.protocol import (
AnyResponseFormat,
OpenAIBaseModel,
PerRequestMetrics,
StopParam,
StreamOptions,
UsageInfo,
structured_outputs_from_response_format,
validate_structural_tag_response_format,
validate_structured_outputs_structural_tag,
)
from vllm.entrypoints.serve.engine.protocol import OpenAIBaseModel, UsageInfo
from vllm.exceptions import VLLMValidationError
from vllm.logger import init_logger
from vllm.logprobs import Logprob
@@ -10,9 +10,12 @@ from typing import cast
from fastapi import Request
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.generate.base.protocol import (
PerRequestMetrics,
RequestResponseMetadata,
)
from vllm.entrypoints.generate.base.serving import (
GenerateBaseServing,
GenerationError,
build_per_request_timing_metrics,
build_spec_decoding_metrics,
clamp_prompt_logprobs,
@@ -26,17 +29,15 @@ from vllm.entrypoints.openai.completion.protocol import (
CompletionResponseStreamChoice,
CompletionStreamResponse,
)
from vllm.entrypoints.openai.engine.protocol import (
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.serve.engine.protocol import (
ErrorResponse,
PerRequestMetrics,
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 VLLMValidationError
from vllm.exceptions import GenerationError, VLLMValidationError
from vllm.inputs import EngineInput
from vllm.logger import init_logger
from vllm.logprobs import Logprob