[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
+1 -1
View File
@@ -26,7 +26,7 @@ from vllm.entrypoints.constants import (
H11_MAX_HEADER_COUNT_DEFAULT,
H11_MAX_INCOMPLETE_EVENT_SIZE_DEFAULT,
)
from vllm.entrypoints.openai.serving_models import LoRAModulePath
from vllm.entrypoints.openai.models.protocol import LoRAModulePath
from vllm.logger import init_logger
from vllm.tool_parsers import ToolParserManager
from vllm.utils.argparse_utils import FlexibleArgumentParser