-
Notifications
You must be signed in to change notification settings - Fork 454
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
(ONNXRuntimeError) LoadLibrary failed with error 126 #618
Comments
Hi @Eichhof, |
Hi @Eichhof, |
Hi @Eichhof , just saw this one in ONNX Runtime issues, I'm wondering if it could be related: microsoft/onnxruntime#14063 |
Thank you very much for the hints. I will test it in the next two days and let you know. |
Hi @michaelbenayoun and @JingyaHuang
|
Now In addition, I'm also getting the same out-of-memory error as above. Probably with FP16 this problem would be solved. Finally, I'm getting also the warning
|
@Eichhof Sorry you encounter all those issues. I hope we can really improve the support for TensorRT in the coming days/weeks. Do you get a
when passing You can safely ignore the warnings:
I recommend you to read the issue #636 if you are using gpt2/gpt-j or alike, it's an issue in transformers and I'll fix ASAP as well. |
@Eichhof did you manage to solve the issue |
@fxmarty Yes, I'm getting exactly this warning when passing In Transformers, I'm using Do you recommend Cuda lazy loading? Yes, the error |
Hi, the PR is ready, and should be merged soon in Unfortunately For Cuda lazy loading, I'm not sure. Given that you get the warning I mentioned above, it's likely CUDAExecutionProvider is actually used. I'll close this issue for now then, feel free to open one for the cuda lazy loading warning message! |
@fxmarty I'm still waiting for the merge of the PR. Do you have any updates when this will be the case? |
Hi @Eichhof , it is merged: #653 and you should be able to pass If there is any other problem you encounter, feel free to open an issue, it's helpful for us to improve the lib and keep track! |
System Info
Who can help?
@JingyaHuang @echarlaix
Information
Tasks
examples
folder (such as GLUE/SQuAD, ...)Reproduction
I Installed optimum with
pip install optimum[onnxruntime-gpu]
. Then I was runningpython -m optimum.exporters.onnx --task causal-lm-with-past --model EleutherAI/gpt-j-6B gptj_onnx/
to transform GPT-J to ONNX. To use the model, I used the following lines:When running these lines of code, I'm getting the following error:
I have installed Cuda 11.6 and also cuDNN 8.7.0.
Expected behavior
The model should load correctly without an error.
The text was updated successfully, but these errors were encountered: