A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 22:15 UTC
[BugFix] Minor: logger import in attention backend (#13706)
Signed-off-by: Andy Lo <andy@mistral.ai>
Andy Lo committed
Feb 23, 2025 at 00:51 UTC
322d2a27d66eb1896272e76640e5dfdec6fb4fcc
1 file changed
+2
-2
vllm/attention/backends/utils.py
+2
-2
@@ -12,12 +12,12 @@ from vllm import envs
12
from vllm.attention import (AttentionMetadata, AttentionMetadataBuilder,
13
AttentionState)
14
from vllm.attention.backends.abstract import AttentionType
15
-from vllm.logger import logging
15
+from vllm.logger import init_logger
16
from vllm.multimodal import MultiModalPlaceholderMap
17
from vllm.platforms import current_platform
18
from vllm.utils import async_tensor_h2d, make_tensor_with_pad
19
20
-logger = logging.getLogger(__name__)
20
+logger = init_logger(__name__)
21
22
if TYPE_CHECKING:
23
from vllm.worker.model_runner_base import ModelRunnerBase