squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix] Fix run_batch logger (#7640)

Browse Source
This commit is contained in:
Pooya Davoodi 2024-08-23 13:58:26 -07:00 committed by GitHub
parent 9db93de20c
commit 6885fde317
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
vllm/entrypoints/openai/run_batch.py
View File

@ -6,7 +6,7 @@ import aiohttp
from vllm.engine.arg_utils import AsyncEngineArgs, nullable_str from vllm.engine.arg_utils import AsyncEngineArgs, nullable_str
from vllm.engine.async_llm_engine import AsyncLLMEngine from vllm.engine.async_llm_engine import AsyncLLMEngine
from vllm.entrypoints.logger import RequestLogger from vllm.entrypoints.logger import RequestLogger, logger
# yapf: disable # yapf: disable
from vllm.entrypoints.openai.protocol import (BatchRequestInput, from vllm.entrypoints.openai.protocol import (BatchRequestInput,
BatchRequestOutput, BatchRequestOutput,
@ -16,13 +16,10 @@ from vllm.entrypoints.openai.protocol import (BatchRequestInput,
# yapf: enable # yapf: enable
from vllm.entrypoints.openai.serving_chat import OpenAIServingChat from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
from vllm.entrypoints.openai.serving_embedding import OpenAIServingEmbedding from vllm.entrypoints.openai.serving_embedding import OpenAIServingEmbedding
from vllm.logger import init_logger
from vllm.usage.usage_lib import UsageContext from vllm.usage.usage_lib import UsageContext
from vllm.utils import FlexibleArgumentParser, random_uuid from vllm.utils import FlexibleArgumentParser, random_uuid
from vllm.version import __version__ as VLLM_VERSION from vllm.version import __version__ as VLLM_VERSION
logger = init_logger(__name__)
def parse_args(): def parse_args():
parser = FlexibleArgumentParser( parser = FlexibleArgumentParser(
@ -184,7 +181,7 @@ async def main(args):
if __name__ == "__main__": if __name__ == "__main__":
args = parse_args() args = parse_args()
logger.info("vLLM API server version %s", VLLM_VERSION) logger.info("vLLM batch processing API version %s", VLLM_VERSION)
logger.info("args: %s", args) logger.info("args: %s", args)
asyncio.run(main(args)) asyncio.run(main(args))