Open codeshop715 opened 5 days ago
I used xformers(version 0.0.28.post1), but the memory usage of the model has not been optimized. With 8 NVIDIA 3090, I still can’t set the batch size to 24. Here is my conda environment:
absl-py 2.1.0
antlr4-python3-runtime 4.8
astunparse 1.6.3
autocommand 2.2.2
backports.tarfile 1.2.0
bitsandbytes 0.38.1
Brotli 1.0.9
certifi 2024.8.30
cffi 1.17.1
charset-normalizer 3.3.2
clip 1.0
colorama 0.4.6
contourpy 1.3.0
cycler 0.12.1
dataclasses 0.8
decorator 4.4.2
einops 0.8.0
filelock 3.13.1
flatbuffers 24.3.25
fonttools 4.54.1
freetype-py 2.5.1
fsspec 2024.2.0
ftfy 6.2.3
future 0.18.3
fvcore 0.1.5.post20221221
gast 0.6.0
google-pasta 0.2.0
grpcio 1.66.2
h5py 3.12.1
huggingface-hub 0.25.1
hydra-core 1.0.0
idna 3.10
imageio 2.35.1
imageio-ffmpeg 0.5.1
importlib_metadata 8.0.0
importlib_resources 6.4.0
inflect 7.3.1
iopath 0.1.10
jaraco.collections 5.1.0
jaraco.context 5.3.0
jaraco.functools 4.0.1
jaraco.text 3.12.1
Jinja2 3.1.3
keras 3.6.0
kiwisolver 1.4.7
libclang 18.1.1
Markdown 3.7
markdown-it-py 3.0.0
MarkupSafe 2.1.5
matplotlib 3.9.2
mdurl 0.1.2
ml-dtypes 0.4.1
more-itertools 10.3.0
moviepy 1.0.3
mpmath 1.3.0
namex 0.0.8
natsort 8.4.0
networkx 3.2.1
numpy 1.23.5
nvidia-cublas-cu12 12.1.3.1
nvidia-cuda-cupti-cu12 12.1.105
nvidia-cuda-nvrtc-cu12 12.1.105
nvidia-cuda-runtime-cu12 12.1.105
nvidia-cudnn-cu12 9.1.0.70
nvidia-cufft-cu12 11.0.2.54
nvidia-curand-cu12 10.3.2.106
nvidia-cusolver-cu12 11.4.5.107
nvidia-cusparse-cu12 12.1.0.106
nvidia-nccl-cu12 2.20.5
nvidia-nvjitlink-cu12 12.1.105
nvidia-nvtx-cu12 12.1.105
omegaconf 2.1.2
opencv-python 4.10.0.84
opt_einsum 3.4.0
optree 0.13.0
packaging 24.1
pandas 1.4.1
peract_colab 0.0.0
pillow 10.4.0
pip 24.2
platformdirs 4.2.2
point_renderer 0.2.0
portalocker 2.10.1
proglog 0.1.10
protobuf 4.25.5
psutil 6.0.0
pycparser 2.21
pyglet 2.0.17
Pygments 2.18.0
PyOpenGL 3.1.0
pyparsing 3.1.4
pyquaternion 0.9.9
pyrender 0.1.45
PyRep 4.1.0.3
PySocks 1.7.1
python-dateutil 2.9.0.post0
pytorch3d 0.7.8
pytz 2024.2
PyYAML 6.0.2
regex 2024.9.11
requests 2.32.3
rich 13.9.1
rlbench 1.2.0
rvt 0.0.1
safetensors 0.4.5
scipy 1.14.1
setproctitle 1.3.3
setuptools 75.1.0
six 1.16.0
sympy 1.12
tabulate 0.9.0
tensorboard 2.17.1
tensorboard-data-server 0.7.2
tensorflow 2.17.0
tensorflow-io-gcs-filesystem 0.37.1
termcolor 2.4.0
timeout-decorator 0.5.0
tokenizers 0.20.0
tomli 2.0.1
torch 2.4.1+cu121
torchaudio 2.4.1+cu121
torchvision 0.19.1+cu121
tqdm 4.66.5
transformers 4.45.1
transforms3d 0.4.2
trimesh 4.4.9
triton 3.0.0
typeguard 4.3.0
typing_extensions 4.12.2
tzdata 2024.2
urllib3 2.2.3
wcwidth 0.2.13
Werkzeug 3.0.4
wheel 0.44.0
wrapt 1.16.0
xformers 0.0.28.post1
yacs 0.1.8
yarr 0.1
zipp 3.19.2
Hi,
Details are here: https://github.com/NVlabs/RVT/issues/45#issuecomment-2197729376
What version of xformers is used?