[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
@@ -32,6 +32,11 @@ from vllm.entrypoints.anthropic.serving import (
AnthropicServingMessages,
_build_anthropic_usage,
)
from vllm.entrypoints.generate.base.protocol import (
DeltaFunctionCall,
DeltaMessage,
DeltaToolCall,
)
from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionResponse,
ChatCompletionResponseChoice,
@@ -39,13 +44,7 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionStreamResponse,
ChatMessage,
)
from vllm.entrypoints.openai.engine.protocol import (
DeltaFunctionCall,
DeltaMessage,
DeltaToolCall,
PromptTokenUsageInfo,
UsageInfo,
)
from vllm.entrypoints.serve.engine.protocol import PromptTokenUsageInfo, UsageInfo
from vllm.entrypoints.serve.exception_handling.handlers.validation import (
validation_exception_handler,
)
+1 -1
View File
@@ -33,8 +33,8 @@ from vllm.entrypoints.cohere.protocol import (
CohereChatV2Response,
)
from vllm.entrypoints.cohere.serving import CohereServingChatV2
from vllm.entrypoints.openai.engine.protocol import ErrorInfo, ErrorResponse
from vllm.entrypoints.scale_out.token_in_token_out.protocol import GenerateRequest
from vllm.entrypoints.serve.engine.protocol import ErrorInfo, ErrorResponse
from vllm.entrypoints.serve.exception_handling.handlers.http import (
http_exception_handler,
)
@@ -24,9 +24,9 @@ from vllm.entrypoints.generate.generative_scoring.serving import (
GenerativeScoringResponse,
ServingGenerativeScoring,
)
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.openai.models.protocol import BaseModelPath
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
from vllm.logprobs import Logprob
from vllm.outputs import CompletionOutput, RequestOutput
from vllm.tokenizers import get_tokenizer
@@ -21,7 +21,7 @@ from vllm.entrypoints.launchers.run_batch import (
make_transcription_wrapper,
upload_data,
)
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
from vllm.exceptions import VLLMValidationError
from vllm.utils.mem_constants import MiB_bytes
@@ -8,13 +8,13 @@ import httpx
import pytest
from tests.utils import RemoteOpenAIServer
from vllm.entrypoints.generate.base.protocol import RequestResponseMetadata
from vllm.entrypoints.openai.chat_completion.batch_serving import (
OpenAIServingChatBatch,
)
from vllm.entrypoints.openai.chat_completion.protocol import (
BatchChatCompletionRequest,
)
from vllm.entrypoints.openai.engine.protocol import RequestResponseMetadata
from vllm.outputs import CompletionOutput, RequestOutput
# any model with a chat template defined in tokenizer_config should work here
@@ -13,11 +13,10 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionRequest,
)
from vllm.entrypoints.openai.chat_completion.serving import OpenAIServingChat
from vllm.entrypoints.openai.engine.protocol import GenerationError
from vllm.entrypoints.openai.models.protocol import BaseModelPath
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.scale_out.render.serving import ServingRender
from vllm.exceptions import VLLMValidationError
from vllm.exceptions import GenerationError, VLLMValidationError
from vllm.outputs import CompletionOutput, RequestOutput
from vllm.renderers.hf import HfRenderer
from vllm.renderers.online_renderer import OnlineRenderer
@@ -20,6 +20,10 @@ from tests.entrypoints.openai.utils import (
from tests.utils import RemoteOpenAIServer
from vllm._aiter_ops import is_aiter_found_and_supported
from vllm.config import MultiModalConfig
from vllm.entrypoints.generate.base.protocol import (
DeltaMessage,
RequestResponseMetadata,
)
from vllm.entrypoints.generate.base.serving import build_per_request_timing_metrics
from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionRequest,
@@ -31,17 +35,13 @@ from vllm.entrypoints.openai.chat_completion.serving import (
_make_completion_tokens_details,
_make_prompt_tokens_details,
)
from vllm.entrypoints.openai.engine.protocol import (
DeltaMessage,
ErrorResponse,
RequestResponseMetadata,
)
from vllm.entrypoints.openai.models.serving import (
BaseModelPath,
OpenAIModelRegistry,
OpenAIServingModels,
)
from vllm.entrypoints.openai.parser.harmony_utils import get_encoding
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
from vllm.exceptions import VLLMValidationError
from vllm.inputs import TokensPrompt
from vllm.multimodal.inputs import PlaceholderRange
@@ -8,16 +8,13 @@ from unittest.mock import AsyncMock, MagicMock
import pytest
from vllm.config.multimodal import MultiModalConfig
from vllm.entrypoints.generate.base.protocol import RequestResponseMetadata
from vllm.entrypoints.openai.completion.protocol import CompletionRequest
from vllm.entrypoints.openai.completion.serving import OpenAIServingCompletion
from vllm.entrypoints.openai.engine.protocol import (
GenerationError,
RequestResponseMetadata,
)
from vllm.entrypoints.openai.models.protocol import BaseModelPath
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.scale_out.render.serving import ServingRender
from vllm.exceptions import VLLMValidationError
from vllm.exceptions import GenerationError, VLLMValidationError
from vllm.outputs import CompletionOutput, RequestOutput
from vllm.renderers.hf import HfRenderer
from vllm.renderers.online_renderer import OnlineRenderer
@@ -11,9 +11,9 @@ import pytest
from vllm.config.multimodal import MultiModalConfig
from vllm.entrypoints.openai.completion.protocol import CompletionRequest
from vllm.entrypoints.openai.completion.serving import OpenAIServingCompletion
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.openai.models.protocol import BaseModelPath
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
from vllm.lora.request import LoRARequest
from vllm.lora.resolver import LoRAResolver, LoRAResolverRegistry
from vllm.renderers.hf import HfRenderer
@@ -7,8 +7,9 @@ from unittest.mock import MagicMock
import pytest
import vllm.envs as envs
from vllm.entrypoints.generate.base.serving import GenerateBaseServing, GenerationError
from vllm.entrypoints.generate.base.serving import GenerateBaseServing
from vllm.envs import disable_envs_cache
from vllm.exceptions import GenerationError
@pytest.mark.asyncio
@@ -11,7 +11,7 @@ from unittest.mock import MagicMock
import pytest
from vllm.entrypoints.openai.engine.protocol import (
from vllm.entrypoints.generate.base.protocol import (
DeltaMessage,
ExtractedToolCallInformation,
FunctionCall,
@@ -25,14 +25,13 @@ from openai.types.responses.tool import (
)
import vllm.envs as envs
from vllm.entrypoints.mcp.tool_server import ToolServer
from vllm.entrypoints.openai.engine.protocol import (
from vllm.entrypoints.generate.base.protocol import (
DeltaFunctionCall,
DeltaMessage,
DeltaToolCall,
ErrorResponse,
RequestResponseMetadata,
)
from vllm.entrypoints.mcp.tool_server import ToolServer
from vllm.entrypoints.openai.responses.context import ConversationContext, SimpleContext
from vllm.entrypoints.openai.responses.protocol import (
ResponseCreatedEvent,
@@ -49,6 +48,7 @@ from vllm.entrypoints.openai.responses.serving import (
from vllm.entrypoints.openai.responses.streaming_events import (
StreamingState,
)
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
from vllm.inputs import tokens_input
from vllm.outputs import CompletionOutput, RequestOutput
from vllm.parser.harmony import Segment
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from vllm.entrypoints.openai.engine.protocol import (
from vllm.entrypoints.generate.base.protocol import (
DeltaFunctionCall,
DeltaMessage,
DeltaToolCall,
@@ -26,9 +26,9 @@ from openai.types.shared import Reasoning
from vllm.config.multimodal import MultiModalConfig
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.openai.responses.protocol import ResponsesRequest
from vllm.entrypoints.openai.responses.serving import OpenAIServingResponses
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
from vllm.inputs import tokens_input
from vllm.renderers.online_renderer import OnlineRenderer
from vllm.renderers.params import ChatParams
@@ -5,6 +5,13 @@ import pytest
from openai.types.chat.chat_completion import ChatCompletion as OpenAIChatCompletion
from openai.types.chat.chat_completion_chunk import ChatCompletionChunk
from vllm.entrypoints.generate.base.protocol import (
DeltaFunctionCall,
DeltaMessage,
DeltaToolCall,
FunctionCall,
ToolCall,
)
from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionRequest,
ChatCompletionResponse,
@@ -13,15 +20,8 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionStreamResponse,
ChatMessage,
)
from vllm.entrypoints.openai.engine.protocol import (
DeltaFunctionCall,
DeltaMessage,
DeltaToolCall,
FunctionCall,
ToolCall,
UsageInfo,
)
from vllm.entrypoints.openai.responses.protocol import ResponsesRequest
from vllm.entrypoints.serve.engine.protocol import UsageInfo
from vllm.parser.abstract_parser import DelegatingParser
pytestmark = pytest.mark.skip_global_cleanup
+1 -1
View File
@@ -10,7 +10,7 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionStreamResponse,
ChatMessage,
)
from vllm.entrypoints.openai.engine.protocol import UsageInfo
from vllm.entrypoints.serve.engine.protocol import UsageInfo
async def accumulate_streaming_response(
@@ -23,6 +23,7 @@ from vllm.entrypoints.scale_out.token_in_token_out.protocol import (
GenerateResponseStreamChoice,
GenerateStreamResponse,
)
from vllm.entrypoints.serve.engine.protocol import ErrorResponse, UsageInfo
MODEL_NAME = "hmellor/tiny-random-LlamaForCausalLM"
@@ -40,7 +41,6 @@ def _make_stream_chunk(
usage: dict | None = None,
) -> GenerateStreamResponse:
"""Build a GenerateStreamResponse SSE chunk."""
from vllm.entrypoints.openai.engine.protocol import UsageInfo
return GenerateStreamResponse(
request_id=request_id,
@@ -61,7 +61,6 @@ def _make_usage_chunk(
request_id: str = "test-req",
) -> GenerateStreamResponse:
"""Build a usage only final SSE chunk (empty choices)."""
from vllm.entrypoints.openai.engine.protocol import UsageInfo
return GenerateStreamResponse(
request_id=request_id,
@@ -473,7 +472,6 @@ class TestServingDerenderStreamErrorHandling:
@pytest.mark.asyncio
@pytest.mark.parametrize("exc", [KeyError("bad byte"), IndexError("oob")])
async def test_completion_stream_bad_state_returns_400(self, exc):
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.scale_out.token_in_token_out.protocol import (
DerenderCompletionStreamRequest,
)
@@ -492,7 +490,6 @@ class TestServingDerenderStreamErrorHandling:
@pytest.mark.asyncio
@pytest.mark.parametrize("exc", [KeyError("bad byte"), IndexError("oob")])
async def test_chat_stream_bad_state_returns_400(self, exc):
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.scale_out.token_in_token_out.protocol import (
DerenderChatStreamRequest,
)
@@ -9,7 +9,7 @@ from unittest.mock import AsyncMock, MagicMock
import pytest
from vllm.config.multimodal import MultiModalConfig
from vllm.entrypoints.openai.engine.protocol import GenerationError, StreamOptions
from vllm.entrypoints.generate.base.protocol import StreamOptions
from vllm.entrypoints.openai.models.protocol import BaseModelPath
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.scale_out.token_in_token_out.protocol import (
@@ -17,6 +17,7 @@ from vllm.entrypoints.scale_out.token_in_token_out.protocol import (
GenerateResponse,
)
from vllm.entrypoints.scale_out.token_in_token_out.serving import ServingTokens
from vllm.exceptions import GenerationError
from vllm.logprobs import Logprob
from vllm.outputs import CompletionOutput, RequestOutput
from vllm.renderers import renderer_from_config
@@ -9,13 +9,11 @@ import pytest
from vllm import PoolingParams
from vllm.config import ModelConfig
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
)
from vllm.entrypoints.openai.models.protocol import BaseModelPath
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.pooling.base.serving import PoolingBaseServing
from vllm.entrypoints.pooling.typing import PoolingServeContext
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
from vllm.entrypoints.serve.lora.protocol import (
LoadLoRAAdapterRequest,
UnloadLoRAAdapterRequest,
@@ -5,7 +5,7 @@ from argparse import Namespace
import pytest
from vllm.entrypoints.openai.engine.protocol import StreamOptions
from vllm.entrypoints.generate.base.protocol import StreamOptions
from vllm.entrypoints.serve.utils import api_utils
from vllm.entrypoints.serve.utils.api_utils import (
get_max_tokens,
@@ -19,11 +19,9 @@ import pytest
from vllm.config import ModelConfig
from vllm.config.speech_to_text import SpeechToTextConfig
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.speech_to_text.base.serving import (
SpeechToTextBaseServing,
asr_inter_chunk_separator,