diff --git a/web/app/docs/hardware/coral-tpu-lxc/page.tsx b/web/app/docs/hardware/coral-tpu-lxc/page.tsx index 234ebb1..3057f10 100644 --- a/web/app/docs/hardware/coral-tpu-lxc/page.tsx +++ b/web/app/docs/hardware/coral-tpu-lxc/page.tsx @@ -11,21 +11,17 @@ export default function CoralTPULXC() { return (
This guide explains how to configure Google Coral TPU support for LXC containers in Proxmox VE using ProxMenux. Coral TPU provides dedicated AI acceleration, improving inference performance for machine learning applications. It is particularly useful for video surveillance applications with real-time video analysis, such as Frigate or Agent DVR or Blue Iris using CodeProject.AI.
- +The script automates the following steps:
-The script automates the complete configuration of Coral TPU support in LXC containers, including USB and M.2 variants. It applies Proxmox-specific container settings, manages device passthrough permissions, and installs required drivers both on the host and inside the container.
+The USB variant uses a persistent mapping based on /dev/coral via udev rules, avoiding reliance on dynamic USB paths like /dev/bus/usb/*. This ensures consistent device assignment across reboots and hardware reordering.
The M.2 version is detected automatically and configured only if present.
+The script installs the necessary components inside the container:
va-driver-allocl-icd-libopencl1intel-opencl-icdvainfointel-gpu-toolspython3python3-pippython3-venvgnupgcurllibedgetpu1-std (standard performance)libedgetpu1-max (maximum performance, optional)/dev/coral created by a udev rule. This improves stability and avoids issues with changing USB port identifiers.lspci and configured only if present.