saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-06-04 23:59:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update stable diffusion demo requirements (#20914)

Browse source 
### Description
Update docker and package version for stable diffusion demo.

### Motivation and Context
Update onnx to 1.16 for security
This commit is contained in:
Tianlei Wu 2024-06-04 12:08:04 -07:00 committed by GitHub
parent 51bc53580d
commit 6dfdef7782
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 12 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
onnxruntime/python/tools/transformers/models/stable_diffusion/README.md
View file

@ -36,16 +36,18 @@ cd onnxruntime
Install nvidia-docker using [these instructions](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#docker).
```
docker run --rm -it --gpus all -v $PWD:/workspace nvcr.io/nvidia/pytorch:23.10-py3 /bin/bash
docker run --rm -it --gpus all -v $PWD:/workspace nvcr.io/nvidia/pytorch:24.04-py3 /bin/bash
```
#### Build onnxruntime from source
The cuDNN in the container might not be compatible with official onnxruntime-gpu package, it is recommended to build from source instead.
After launching the docker, you can build and install onnxruntime-gpu wheel like the following.
```
export CUDACXX=/usr/local/cuda-12.2/bin/nvcc
export CUDACXX=/usr/local/cuda/bin/nvcc
git config --global --add safe.directory '*'
sh build.sh --config Release --build_shared_lib --parallel --use_cuda --cuda_version 12.2 \
--cuda_home /usr/local/cuda-12.2 --cudnn_home /usr/lib/x86_64-linux-gnu/ --build_wheel --skip_tests \
sh build.sh --config Release --build_shared_lib --parallel --use_cuda --cuda_version 12.4 \
--cuda_home /usr/local/cuda --cudnn_home /usr/lib/x86_64-linux-gnu/ --build_wheel --skip_tests \
--use_tensorrt --tensorrt_home /usr/src/tensorrt \
--cmake_extra_defines onnxruntime_BUILD_UNIT_TESTS=OFF \
--cmake_extra_defines CMAKE_CUDA_ARCHITECTURES=80 \

2
onnxruntime/python/tools/transformers/models/stable_diffusion/requirements-cuda11.txt
View file

@ -6,7 +6,7 @@ onnxruntime-gpu>=1.16.2
py3nvml
# The version of cuda-python shall be compatible with installed CUDA version.
# For example, if your CUDA version is 12.1, you can install cuda-python 12.1.
# For demo of TensorRT excution provider and TensortRT.
cuda-python==11.8.0
# For windows, cuda-python need the following

2
onnxruntime/python/tools/transformers/models/stable_diffusion/requirements-cuda12.txt
View file

@ -6,7 +6,7 @@
py3nvml
# The version of cuda-python shall be compatible with installed CUDA version.
# For example, if your CUDA version is 12.1, you can install cuda-python 12.1.
# For demo of TensorRT excution provider and TensortRT.
cuda-python>=12.1.0
# For windows, cuda-python need the following

8
onnxruntime/python/tools/transformers/models/stable_diffusion/requirements.txt
View file

@ -1,8 +1,8 @@
diffusers==0.24.0
transformers==4.38.0
diffusers==0.28.0
transformers==4.41.2
numpy>=1.24.1
accelerate
onnx==1.14.1
onnx==1.16.0
coloredlogs
packaging
# Use newer version of protobuf might cause crash
@ -11,7 +11,7 @@ psutil
sympy
controlnet_aux==0.0.7
# The following are for SDXL
optimum==1.14.1
optimum==1.20.0
safetensors
invisible_watermark
# newer version of opencv-python migth encounter module 'cv2.dnn' has no attribute 'DictValue' error