[Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
Chauncey
2026-01-13 13:01:39 +00:00
committed by GitHub
parent a5bbbd2f24
commit fefce49807
128 changed files with 1221 additions and 1008 deletions
+4 -2
View File
@@ -19,13 +19,15 @@ from tqdm import tqdm
from vllm.engine.arg_utils import AsyncEngineArgs, optional_type
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.logger import RequestLogger
from vllm.entrypoints.openai.protocol import (
from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionRequest,
ChatCompletionResponse,
)
from vllm.entrypoints.openai.chat_completion.serving import OpenAIServingChat
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
OpenAIBaseModel,
)
from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
from vllm.entrypoints.openai.serving_models import BaseModelPath, OpenAIServingModels
from vllm.entrypoints.pooling.embed.protocol import EmbeddingRequest, EmbeddingResponse
from vllm.entrypoints.pooling.embed.serving import OpenAIServingEmbedding