[Refactor] [10/N] to simplify the vLLM openai completion serving architecture (#32369)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
Chauncey
2026-01-15 07:41:34 +00:00
committed by GitHub
parent ae1eba6a9a
commit 4c1c501a7e
43 changed files with 777 additions and 642 deletions
+2 -1
View File
@@ -12,7 +12,8 @@ from vllm.config.multimodal import MultiModalConfig
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 ErrorResponse
from vllm.entrypoints.openai.serving_models import BaseModelPath, OpenAIServingModels
from vllm.entrypoints.openai.models.protocol import BaseModelPath
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.outputs import CompletionOutput, RequestOutput
from vllm.tokenizers import get_tokenizer
from vllm.v1.engine.async_llm import AsyncLLM
+1 -1
View File
@@ -6,7 +6,7 @@ import json
import pytest
from vllm.entrypoints.openai.cli_args import make_arg_parser, validate_parsed_serve_args
from vllm.entrypoints.openai.serving_models import LoRAModulePath
from vllm.entrypoints.openai.models.protocol import LoRAModulePath
from vllm.utils.argparse_utils import FlexibleArgumentParser
from ...utils import VLLM_PATH
@@ -9,9 +9,11 @@ from unittest.mock import AsyncMock, MagicMock
import pytest
from vllm.config.multimodal import MultiModalConfig
from vllm.entrypoints.openai.engine.protocol import CompletionRequest, ErrorResponse
from vllm.entrypoints.openai.serving_completion import OpenAIServingCompletion
from vllm.entrypoints.openai.serving_models import BaseModelPath, OpenAIServingModels
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.outputs import CompletionOutput, RequestOutput
from vllm.tokenizers import get_tokenizer
from vllm.v1.engine.async_llm import AsyncLLM
@@ -8,13 +8,11 @@ from unittest.mock import Mock
import pytest
from vllm.entrypoints.openai.engine.protocol import (
StructuredOutputsParams,
)
from vllm.entrypoints.tool_server import ToolServer
from vllm.reasoning.gptoss_reasoning_parser import (
GptOssReasoningParser,
)
from vllm.sampling_params import StructuredOutputsParams
class TestGptOssStructuralTagsIntegration:
@@ -9,9 +9,11 @@ from unittest.mock import AsyncMock, MagicMock
import pytest
from vllm.config.multimodal import MultiModalConfig
from vllm.entrypoints.openai.engine.protocol import CompletionRequest, ErrorResponse
from vllm.entrypoints.openai.serving_completion import OpenAIServingCompletion
from vllm.entrypoints.openai.serving_models import BaseModelPath, OpenAIServingModels
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.lora.request import LoRARequest
from vllm.lora.resolver import LoRAResolver, LoRAResolverRegistry
from vllm.tokenizers import get_tokenizer
@@ -20,8 +20,8 @@ from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
RequestResponseMetadata,
)
from vllm.entrypoints.openai.models.serving import BaseModelPath, OpenAIServingModels
from vllm.entrypoints.openai.parser.harmony_utils import get_encoding
from vllm.entrypoints.openai.serving_models import BaseModelPath, OpenAIServingModels
from vllm.outputs import CompletionOutput, RequestOutput
from vllm.tokenizers import get_tokenizer
from vllm.tool_parsers import ToolParserManager
@@ -9,7 +9,7 @@ import pytest
from vllm.config import ModelConfig
from vllm.entrypoints.openai.engine.serving import OpenAIServing
from vllm.entrypoints.openai.serving_models import OpenAIServingModels
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.tokenizers.mistral import MistralTokenizer
@@ -11,7 +11,8 @@ from vllm.engine.protocol import EngineClient
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
)
from vllm.entrypoints.openai.serving_models import BaseModelPath, OpenAIServingModels
from vllm.entrypoints.openai.models.protocol import BaseModelPath
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.serve.lora.protocol import (
LoadLoRAAdapterRequest,
UnloadLoRAAdapterRequest,