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 16, 18:15 UTC
[misc][cuda] add warning for pynvml user (#7675)
youkaichao committed
Aug 20, 2024 at 00:35 UTC
ad28a74beb8497a6961cfb39c63d6070712f1ef7
1 file changed
+6
vllm/platforms/cuda.py
+6
@@ -18,6 +18,12 @@ logger = init_logger(__name__)
18
_P = ParamSpec("_P")
19
_R = TypeVar("_R")
20
21
+if pynvml.__file__.endswith("__init__.py"):
22
+ logger.warning(
23
+ "You are using a deprecated `pynvml` package. Please install"
24
+ " `nvidia-ml-py` instead. See https://pypi.org/project/pynvml "
25
+ "for more information.")
26
+
27
# NVML utils
28
# Note that NVML is not affected by `CUDA_VISIBLE_DEVICES`,
29
# all the related functions work on real physical device ids.