apextoaster
/
onnx-web
1
0
Fork 0
Code Actions

feat(api): experimentally add CUDA provider and Nvidia platform

This commit is contained in:
Sean Sube 2023-01-07 08:56:21 -06:00
parent bb77d45ec6
commit 8359bd5b99
2 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
README.md
View File

@ -1,9 +1,10 @@
# ONNX Web
This is a web UI for running ONNX models with GPU acceleration locally or on a remote machine.
This is a web UI for running ONNX models with GPU acceleration or in software, running locally or on a remote machine.
The API runs on both Linux and Windows and provides access to the major functionality of `diffusers`, metadata
about the available models and accelerators, and the output of previous runs.
The API runs on both Linux and Windows and provides access to the major functionality of `diffusers`, along with
metadata about the available models and accelerators, and the output of previous runs. Hardware acceleration is
supported for AMD and experimental for Nvidia, with a CPU fallback capable of running on laptop-class machines.
The GUI runs in all major browsers, including on mobile devices, and allows you to select the model and accelerator
being used, along with the prompt and other image parameters. The last few output images are shown, making it easy to

1
api/onnx_web/serve.py
View File

@ -43,6 +43,7 @@ last_pipeline_scheduler = None
platform_providers = {
'amd': 'DmlExecutionProvider',
'cpu': 'CPUExecutionProvider',
'nvidia': 'CUDAExecutionProvider',
}
pipeline_schedulers = {
'ddim': DDIMScheduler,