[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
+5 -3
View File
@@ -43,20 +43,21 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionRequest,
ChatCompletionResponse,
)
from vllm.entrypoints.openai.engine.protocol import (
from vllm.entrypoints.openai.completion.protocol import (
CompletionRequest,
CompletionResponse,
)
from vllm.entrypoints.openai.engine.protocol import (
ErrorInfo,
ErrorResponse,
FunctionCall,
FunctionDefinition,
VLLMValidationError,
)
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.openai.responses.protocol import (
ResponseInputOutputItem,
ResponsesRequest,
)
from vllm.entrypoints.openai.serving_models import OpenAIServingModels
from vllm.entrypoints.openai.translations.protocol import (
TranscriptionRequest,
TranscriptionResponse,
@@ -95,6 +96,7 @@ from vllm.entrypoints.serve.tokenize.protocol import (
TokenizeResponse,
)
from vllm.entrypoints.utils import _validate_truncation_size, sanitize_message
from vllm.exceptions import VLLMValidationError
from vllm.inputs.data import PromptType, TokensPrompt
from vllm.inputs.parse import (
PromptComponents,