Upgrade to onnxruntime 0.19 #753
Conversation
| RUN python3 -m pip install --extra-index-url https://download.pytorch.org/whl/cu118 \ | ||
| RUN python3 -m pip install \ | ||
| --extra-index-url https://download.pytorch.org/whl/cu118 \ | ||
| --extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-11/pypi/simple/ \ |
There was a problem hiding this comment.
what is this guy doing? changing the default cuda version for onnxruntime? so onnxruntime installs cuda?
There was a problem hiding this comment.
The default is now to install the onnxruntime that's compatible with CUDA 12; this forces it to install the one built for CUDA 11 instead. (It used to be the reverse; you had to choose the channel for CUDA 12 and the default was 11)
| @@ -264,7 +264,7 @@ | |||
|
|
|||
| ONNXRUNTIME_EXECUTION_PROVIDERS = os.getenv( | |||
| "ONNXRUNTIME_EXECUTION_PROVIDERS", | |||
| "[CUDAExecutionProvider,OpenVINOExecutionProvider,CPUExecutionProvider]", | |||
| "[CUDAExecutionProvider,OpenVINOExecutionProvider,CoreMLExecutionProvider,CPUExecutionProvider]", | |||
There was a problem hiding this comment.
now everyone not on a mac is gonna get stupid warnings about not having coremlexecution provider :)
There was a problem hiding this comment.
Yeh I was thinking we should probably update this default to be what onnxruntime.get_available_providers() reports but was going to do that in a different PR.
|
Update: tests have all passed & containers build. 
|
yeldarby
requested review from
PawelPeczek-Roboflow,
grzegorz-roboflow and
hansent
as code owners
Description
This pulls up our dependencies the the latest onnxruntime and updates our Docker containers to match.
Benefits:
Type of change
How has this change been tested, please provide a testcase or example of how you tested the change?
Have run the tests locally. About to build all the containers via our github actions.
Any specific deployment considerations
No.
Docs