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
Inconsistency in CUDA compatibility check #3382
Comments
Is this directly related to Triton? Or is this a check that the container runs before starting Triton? |
It may be in the container, but I don't know where to report problems in Nvidia's containers. It's also worth keeping in mind that Triton explicitly recommends using |
What is the command you use to start the container? |
|
Thanks for the report! This is now fixed this for our 22.01 containers. |
Description
Datacenter GPUs should be able to run the Triton server using forward compatibility drivers. However, if extra libraries are specified in
LD_PRELOAD
(as suggested in https://github.com/triton-inference-server/server/blob/main/docs/custom_operations.md), the compatibility check can fail because of inconsistencies betweenLD_LIBRARY_PATH
andLD_PRELOAD
.Triton Information
What version of Triton are you using? 2.11.0
Are you using the Triton container or did you build it yourself? Started from Triton container and added PyTorch extension libraries on top: fastml/triton-torchgeo:21.06-py3-geometric
To Reproduce
Run the container interactively and enter the following commands:
(LD_LIBRARY_PATH=/usr/local/cuda/compat/lib.real; /usr/local/bin/cudaCheck)
The output is:
This command is obtained from
/etc/shinit_v2
in the Triton container:Expected behavior
The right answer can be obtained from this command:
The output is:
If the compatibility check is going to clear everything out of
LD_LIBRARY_PATH
, it should also clearLD_PRELOAD
for consistency, as indicated above. (Or, it should append/prepend toLD_LIBRARY_PATH
for the check.)The text was updated successfully, but these errors were encountered: