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

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2026-01-13 21:01:39 +08:00
parent a5bbbd2f24
commit fefce49807
128 changed files with 1221 additions and 1008 deletions
--- a/tests/entrypoints/openai/test_serving_engine.py
+++ b/tests/entrypoints/openai/test_serving_engine.py
@@ -8,7 +8,7 @@ from unittest.mock import Mock
 import pytest

 from vllm.config import ModelConfig
-from vllm.entrypoints.openai.serving_engine import OpenAIServing
+from vllm.entrypoints.openai.engine.serving import OpenAIServing
 from vllm.entrypoints.openai.serving_models import OpenAIServingModels
 from vllm.tokenizers.mistral import MistralTokenizer