deepjavalibrary
Does DJL support NVIDIA GeForce RTX 5080？
It seems the 5080 requires CUDA >= 12.8, but DJL only supports up to 12.4.
GPU 处理器： NVIDIA GeForce RTX 5080 驱动程序版本： 572.70 驱动器类型： DCH
The following error occurred when using PyTorch:
Caused by: ai.djl.engine.EngineException: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
I would think so. I made it work on my 4080. You need cuda-toolkit (in your case 12.8). To be fair I ran it on Linux and not on Windows. Cuda is downwards compatible. I even ran it with cuda-toolkit 13.0.
