没法用gpu跑

[Leeying9]

能加载模型，但是占用的是cpu，不是gpu。
在跑之前已经指定了gpu，1，2，3
在跑之前测试过print(torch.cuda.is_available()) #返回 True。
在跑之前看过torch版本：'2.0.1+cu117'
能用的卡是：
[1] Tesla V100-SXM2-32GB | 47°C, 0 % | 0 / 32768 MB |
[2] Tesla V100-SXM2-32GB | 43°C, 0 % | 3 / 32768 MB |
[3] Tesla V100-SXM2-32GB |

下面是运行时的显示：
第一次：
(salmonn) [yli@bogon SALMONN-main]$ python3 web_demo.py --cfg-path configs/decode_config.yaml

===================================BUG REPORT===================================
Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues
For effortless bug reporting copy-paste your error into this form: https://docs.google.com/forms/d/e/1FAIpQLScPB8emS3Thkp66nvqwmjTEgxp8Y9ufuWTzFyr9kJ5AoI47dQ/viewform?usp=sf_link

/home/yli/anaconda3/envs/salmonn/lib/python3.9/site-packages/bitsandbytes/cuda_setup/paths.py:93: UserWarning: /home/yli/anaconda3/envs/salmonn did not contain libcudart.so as expected! Searching further paths...
warn(
/home/yli/anaconda3/envs/salmonn/lib/python3.9/site-packages/bitsandbytes/cuda_setup/paths.py:105: UserWarning: /data/lb_x/gcc10.1/lib64:/data/lb_x/gcc10.1/lib64:/data/lb_x/gcc10.1/lib64: did not contain libcudart.so as expected! Searching further paths...
warn(
/home/yli/anaconda3/envs/salmonn/lib/python3.9/site-packages/bitsandbytes/cuda_setup/paths.py:27: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('https'), PosixPath('//hf-mirror.com')}
warn(
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching /usr/local/cuda/lib64...
CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so
CUDA SETUP: Highest compute capability among GPUs detected: 7.0
CUDA SETUP: Detected CUDA version 111
CUDA SETUP: Loading binary /home/yli/anaconda3/envs/salmonn/lib/python3.9/site-packages/bitsandbytes/libbitsandbytes_cuda111_nocublaslt.so...
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████| 3/3 [00:28<00

第二次：
(salmonn) [yli@bogon SALMONN-main]$ python3 web_demo.py --cfg-path configs/decode_config.yaml

===================================BUG REPORT===================================
Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues
For effortless bug reporting copy-paste your error into this form: https://docs.google.com/forms/d/e/1FAIpQLScPB8emS3Thkp66nvqwmjTEgxp8Y9ufuWTzFyr9kJ5AoI47dQ/viewform?usp=sf_link

/home/yli/anaconda3/envs/salmonn/lib/python3.9/site-packages/bitsandbytes/cuda_setup/paths.py:93: UserWarning: /home/yli/anaconda3/envs/salmonn did not contain libcudart.so as expected! Searching further paths...
warn(
/home/yli/anaconda3/envs/salmonn/lib/python3.9/site-packages/bitsandbytes/cuda_setup/paths.py:105: UserWarning: /data/lb_x/gcc10.1/lib64:/data/lb_x/gcc10.1/lib64:/data/lb_x/gcc10.1/lib64: did not contain libcudart.so as expected! Searching further paths...
warn(
/home/yli/anaconda3/envs/salmonn/lib/python3.9/site-packages/bitsandbytes/cuda_setup/paths.py:27: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('https'), PosixPath('//hf-mirror.com')}
warn(
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching /usr/local/cuda/lib64...
CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so
CUDA SETUP: Highest compute capability among GPUs detected: 7.0
CUDA SETUP: Detected CUDA version 111
CUDA SETUP: Loading binary /home/yli/anaconda3/envs/salmonn/lib/python3.9/site-packages/bitsandbytes/libbitsandbytes_cuda111_nocublaslt.so...
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████| 3/3 [00:28<00:00, 9.64s/it]