We are using docker as container engine (25.0.3) and configured container runtime according to document https://github.com/NVIDIA/k8s-device-plugin?tab=readme-ov-file#enabling-gpu-support-in-kubernetes and deployed helm char after configuring the runclass but we are getting below error for device plugin pod in CrashLoopBackOff, please help us here to resolve the issue.
Error:2024/04/08 11:30:00 Retreiving plugins.2024/04/08 11:30:00 Detected non-NVML platform: could not load NVML: libnvidia-ml.so.1: cannot open shared object file: No such file or directory2024/04/08 11:30:00 Detected non-Tegra platform: /sys/devices/soc0/family file not found2024/04/08 11:30:00 Incompatible platform detected2024/04/08 11:30:00 If this is a GPU node, did you configure the NVIDIA Container Toolkit?2024/04/08 11:30:00 You can check the prerequisites at: https://github.com/NVIDIA/k8s-device-plugin#prerequisites2024/04/08 11:30:00 You can learn how to set the runtime at: https://github.com/NVIDIA/k8s-device-plugin#quick-start2024/04/08 11:30:00 If this is not a GPU node, you should set up a toleration or nodeSelector to only deploy this plugin on GPU nodes2024/04/08 11:30:00 Error: error starting plugins: error getting plugins: unable to load resource managers to manage plugin devices: platform detection failed