-
Notifications
You must be signed in to change notification settings - Fork 1.5k
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
onnx model causes core dump in 22.08+, works with 22.06 #5084
Comments
work-around for #475 & triton-inference-server/server#5084 Authors: - David Gardner (https://github.com/dagardner-nv) Approvers: - Bhargav Suryadevara (https://github.com/bsuryadevara) URL: #477
Hi @dagardner-nv , Thanks for filing this issue with detailed repro steps. One observation is I believe this is segfaulting from one of your TRT models, not the ONNX model. This is noticed from the backtrace reporting calls from the TRT backend. If I load only the ONNX model you mention, it loads successfully:
If I load the corresponding TRT model, it segfaults:
But there is no model in this dir, per the README description mentioning portability/generation of the TRT engine:
Next steps:
ref: DLIS-4353 |
@rmccorm4 good catch. I can confirm that:
I've actually never generated those models before, I did so, I get a core dump, but I also get some errors first. Launching with:
gets:
|
This is a standard TensorRT error. You need to make sure the TRT engines are generated in the same environment (OS, TensorRT version, Compute Capability, etc.) that you deploy Triton in. ex: Generate the TRT engines in the
If you enable I'll wait for the steps to reproduce the engine file if you need help in validating this part. |
Just an FYI, the autocomplete segfault above may already be fixed in the 22.12 release with this commit: triton-inference-server/tensorrt_backend#52. |
… from-source users can use the provided scripts to perform the launching Add --disable-auto-complete-config to launch to work-around triton issue triton-inference-server/server#5084 Add instructions for launching with only an explicit model
I can confirm that auto-complete segfault issue has been fixed. In the absence of a TRT model, triton correctly fails with the following logs:
|
Description
In Morpheus we have an onnx model which was working with tritonserver 22.02 & 22.06 but causes a core dump in versions 22.08, 22.09 & 22.10
nv-morpheus/Morpheus#475
Triton Information
22.08
Container: nvcr.io/nvidia/tritonserver:22.08-py3
To Reproduce
Fails with:
backtrace:
config.pbtxt looks like:
Expected behavior
Not core dumping
The text was updated successfully, but these errors were encountered: