[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
@@ -14,8 +14,8 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionResponse,
)
from vllm.entrypoints.openai.chat_completion.serving import OpenAIServingChat
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,
@@ -9,6 +9,7 @@ from http import HTTPStatus
from fastapi import Request
from vllm.entrypoints.chat_utils import ConversationMessage
from vllm.entrypoints.generate.base.protocol import RequestResponseMetadata
from vllm.entrypoints.openai.chat_completion.protocol import (
BatchChatCompletionRequest,
ChatCompletionResponse,
@@ -16,11 +17,7 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
ChatMessage,
)
from vllm.entrypoints.openai.chat_completion.serving import OpenAIServingChat
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
RequestResponseMetadata,
UsageInfo,
)
from vllm.entrypoints.serve.engine.protocol import ErrorResponse, UsageInfo
from vllm.entrypoints.serve.utils.api_utils import get_max_tokens
from vllm.inputs import EngineInput
from vllm.logger import init_logger
@@ -23,21 +23,20 @@ from vllm.entrypoints.chat_utils import (
ChatCompletionMessageParam,
ChatTemplateContentFormatOption,
)
from vllm.entrypoints.openai.engine.protocol import (
from vllm.entrypoints.generate.base.protocol import (
AnyResponseFormat,
DeltaMessage,
FunctionCall,
FunctionDefinition,
OpenAIBaseModel,
PerRequestMetrics,
StopParam,
StreamOptions,
ToolCall,
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
@@ -16,9 +16,15 @@ from vllm.entrypoints.chat_utils import (
ConversationMessage,
make_tool_call_id,
)
from vllm.entrypoints.generate.base.protocol import (
DeltaMessage,
FunctionCall,
PerRequestMetrics,
RequestResponseMetadata,
ToolCall,
)
from vllm.entrypoints.generate.base.serving import (
GenerateBaseServing,
GenerationError,
build_per_request_timing_metrics,
build_spec_decoding_metrics,
clamp_prompt_logprobs,
@@ -36,23 +42,19 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionStreamResponse,
ChatMessage,
)
from vllm.entrypoints.openai.engine.protocol import (
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.serve.engine.protocol import (
CompletionTokenUsageInfo,
DeltaMessage,
ErrorResponse,
FunctionCall,
PerRequestMetrics,
PromptTokenUsageInfo,
RequestResponseMetadata,
ToolCall,
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.entrypoints.serve.utils.tool_calls_utils import (
maybe_filter_parallel_tool_calls,
)
from vllm.exceptions import GenerationError
from vllm.inputs import EngineInput, MultiModalPlaceholders
from vllm.logger import init_logger
from vllm.logprobs import Logprob