After installing the ultralytics library, GPU usage decreased by half and Ksample time doubled

[ZhenshengWu]

Your question

I am using the most basic SDdemo, and the performance during inference is shown below. The Ksampler phase only took 0.85 seconds，GPU usage rate is close to 100% However, when I installed ultralytics and added a line "from ultralytics import YOLO" in node. py without instantiating "YOLO", the speed of Ksampler increased significantly, while GPU usage dropped to around 50% This issue exists on both my 4090 and A800, but when I commented out this line, it returned to normal I cannot find any reason or solution I also raised this issue in Ultralytics' code repository

Logs

A800 
    Driver Version: 550.54.14
    CUDA Version: 12.4 
GTX4090 
    Driver Version: 535.161.08
    CUDA Version: 12.2

absl-py                   2.1.0
accelerate                0.32.1
addict                    2.4.0
aiohttp                   3.9.5
aiohttp-sse               2.2.0
aiosignal                 1.3.1
albucore                  0.0.13
albumentations            1.4.13
annotated-types           0.7.0
archspec                  0.2.1
asttokens                 2.0.5
astunparse                1.6.3
async-timeout             4.0.3
attrs                     23.1.0
backcall                  0.2.0
basicsr                   1.4.2
beautifulsoup4            4.12.2
bitsandbytes              0.43.1
boltons                   23.0.0
boto3                     1.34.156
botocore                  1.34.156
Brotli                    1.0.9
certifi                   2023.11.17
cffi                      1.16.0
chardet                   4.0.0
charset-normalizer        2.0.4
click                     8.1.7
coloredlogs               15.0.1
conda                     23.9.0
conda-build               3.28.1
conda-content-trust       0.2.0
conda_index               0.3.0
conda-libmamba-solver     23.7.0
conda-package-handling    2.2.0
conda_package_streaming   0.9.0
contourpy                 1.2.1
cryptography              41.0.7
cycler                    0.12.1
Cython                    3.0.11
datasets                  2.20.0
decorator                 5.1.1
deepdiff                  7.0.1
deepspeed                 0.14.4
diffusers                 0.30.0.dev0
dill                      0.3.8
distro                    1.8.0
dnspython                 2.4.2
docker-pycreds            0.4.0
easydict                  1.13
einops                    0.8.0
eval_type_backport        0.2.0
exceptiongroup            1.0.4
executing                 0.8.3
expecttest                0.1.6
filelock                  3.13.1
flatbuffers               24.3.25
fonttools                 4.53.1
frozenlist                1.4.1
fsspec                    2023.12.2
ftfy                      6.2.0
future                    1.0.0
gitdb                     4.0.11
GitPython                 3.1.43
gmpy2                     2.1.2
grpcio                    1.65.0
hjson                     3.1.0
huggingface-hub           0.23.4
humanfriendly             10.0
hypothesis                6.92.0
idna                      3.4
imageio                   2.34.2
importlib_metadata        8.0.0
insightface               0.7.3
ipython                   8.15.0
jedi                      0.18.1
Jinja2                    3.1.2
jmespath                  1.0.1
joblib                    1.4.2
jsonpatch                 1.32
jsonpath-ng               1.6.1
jsonpointer               2.1
jsonschema                4.19.2
jsonschema-specifications 2023.7.1
kiwisolver                1.4.5
kornia                    0.7.3
kornia_rs                 0.1.5
lazy_loader               0.4
libarchive-c              2.9
libmambapy                1.5.3
lmdb                      1.5.1
Markdown                  3.6
MarkupSafe                2.1.1
matplotlib                3.9.1.post1
matplotlib-inline         0.1.6
menuinst                  2.0.1
mkl-fft                   1.3.8
mkl-random                1.2.4
mkl-service               2.4.0
more-itertools            10.1.0
mpmath                    1.3.0
multidict                 6.0.5
multiprocess              0.70.16
networkx                  3.1
ninja                     1.11.1.1
numpy                     1.26.2
nvidia-ml-py              12.555.43
onnx                      1.16.2
onnxruntime               1.18.1
opencv-python             4.6.0.66
opencv-python-headless    4.10.0.84
ordered-set               4.1.0
packaging                 23.1
pandas                    2.2.2
parso                     0.8.3
peft                      0.7.0
pexpect                   4.8.0
pickleshare               0.7.5
piexif                    1.1.3
Pillow                    10.0.1
pip                       23.3.1
pkginfo                   1.9.6
platformdirs              3.10.0
pluggy                    1.0.0
ply                       3.11
prettytable               3.10.2
prompt-toolkit            3.0.36
protobuf                  4.25.3
psutil                    5.9.0
ptyprocess                0.7.0
pure-eval                 0.2.2
py-cpuinfo                9.0.0
pyarrow                   16.1.0
pyarrow-hotfix            0.6
pycosat                   0.6.6
pycparser                 2.21
pydantic                  2.8.2
pydantic_core             2.20.1
Pygments                  2.15.1
pyOpenSSL                 23.2.0
pyparsing                 3.1.2
PySocks                   1.7.1
python-dateutil           2.9.0.post0
python-etcd               0.4.5
pytz                      2023.3.post1
PyYAML                    6.0.1
referencing               0.30.2
regex                     2024.5.15
requests                  2.32.3
rpds-py                   0.10.6
ruamel.yaml               0.17.21
ruamel.yaml.clib          0.2.6
s3transfer                0.10.2
safetensors               0.4.3
scikit-image              0.24.0
scikit-learn              1.5.1
scipy                     1.14.0
seaborn                   0.13.2
sentencepiece             0.2.0
sentry-sdk                2.9.0
setproctitle              1.3.3
setuptools                68.2.2
six                       1.16.0
smmap                     5.0.1
sortedcontainers          2.4.0
soundfile                 0.12.1
soupsieve                 2.5
spandrel                  0.3.4
stack-data                0.2.0
sympy                     1.12
tb-nightly                2.18.0a20240807
tensorboard               2.17.0
tensorboard-data-server   0.7.2
threadpoolctl             3.5.0
tifffile                  2024.7.24
tokenizers                0.19.1
tomli                     2.0.1
toolz                     0.12.0
torch                     2.1.2
torchaudio                2.1.2
torchelastic              0.2.2
torchsde                  0.2.6
torchvision               0.16.2
tqdm                      4.66.4
traitlets                 5.7.1
trampoline                0.1.2
transformers              4.42.3
triton                    2.1.0
truststore                0.8.0
types-dataclasses         0.6.6
typing_extensions         4.12.2
tzdata                    2024.1
ultralytics               8.2.74
ultralytics-thop          2.0.0
urllib3                   1.26.18
wandb                     0.17.4
wcwidth                   0.2.13
Werkzeug                  3.0.3
wheel                     0.41.2
xformers                  0.0.23.post1
xxhash                    3.4.1
yapf                      0.40.2
yarl                      1.9.4
zipp                      3.19.2
zstandard                 0.19.0

Other

No response