RuntimeError: Found no NVIDIA driver on your system.
⏩Queue
Hello, I'm trying to run Hunyuan2 on serverless using queue, but whatever i try, I'm getting RuntimeError: Found no NVIDIA driver on your system.
I've already tried to set cuda version that runpod using to 12.4(same error), then 12.6-12.8(same error)
I also attached my dockerfile
I tried to connect to worker via ssh and using nvidia-smi command I'm getting
-- RUNPOD.IO --
Enjoy your Pod #z2bat2z4v3q8rq ^_^
(base) root@db9e675c887b:/workspace# nvidia-smi
NVIDIA-SMI couldn't find libnvidia-ml.so library in your system. Please make sure that the NVIDIA Display Driver is properly installed and present in your system.
Please also try adding directory that contains libnvidia-ml.so to your system PATH.
I've already tried to set cuda version that runpod using to 12.4(same error), then 12.6-12.8(same error)
I also attached my dockerfile
I tried to connect to worker via ssh and using nvidia-smi command I'm getting
-- RUNPOD.IO --
Enjoy your Pod #z2bat2z4v3q8rq ^_^
(base) root@db9e675c887b:/workspace# nvidia-smi
NVIDIA-SMI couldn't find libnvidia-ml.so library in your system. Please make sure that the NVIDIA Display Driver is properly installed and present in your system.
Please also try adding directory that contains libnvidia-ml.so to your system PATH.
message.txt5KB
