[Refactor] [10/N] to simplify the vLLM openai completion serving architecture (#32369)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user