Open dwctic opened 2 months ago
Hi, djl! One of our developers actually has the same error with torch_cuda.dll
with 0.30.0 version. MSVC 2019 is installed too.
There is no such problem with 0.29.0
@dwctic, could you try running the examples with djl 0.29.0? What if we have the same issue :smile:
Please try one of two solutions that worked in my particular case:
A) Have no CUDA installed on your system (and have no CUDA paths set in your systems Environment Variables), then it hopefully will automatically detect the correct location of the CUDA path, if it is assume that it is managed by the DeepJavaLibrary and the system will also somehow find all dependencies.
B) (If you have multiple CUDA installed on your system) Add C:\Users\USER\.djl.ai\pytorch\CUDA-VERSION
(in my case it was C:\Users\USER\.djl.ai\pytorch\2.4.0-cu124-win-x86_64
) to "PATH" in Windows 10 Environment Variables. Can be done via searching for environment variables and manually adding the folder path. See https://www.howtogeek.com/787217/how-to-edit-environment-variables-on-windows-10-or-11/
Description
When running examples in 0.30.0-SNAPSHOT I receive an UnsatisfiedLinkError.
Expected Behavior
I expect the examples to run.
Error Message
Steps to reproduce
Run the ai.djl.examples.training.TrainTicTacToeTest class
What have you tried to solve it?
Environment Info
Please run the command
./gradlew debugEnv
from the root directory of DJL (if necessary, clone DJL first). It will output information about your system, environment, and installation that can help us debug your issue. Paste the output of the command below: