From 9a0d8528b0f8afca4f98b6051e6db4f0a208b7b4 Mon Sep 17 00:00:00 2001 From: Donato Capitella Date: Wed, 6 Aug 2025 09:33:13 +0100 Subject: [PATCH] Updated README with instructions to clear old toolboxes --- README.md | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/README.md b/README.md index d2d4f9c..50d09e0 100644 --- a/README.md +++ b/README.md @@ -84,6 +84,15 @@ To use Llama.cpp with hardware acceleration inside a toolbox container, you must > * Extra groups (`video`, `render`, `sudo`) may be required for full access to GPU nodes and compute features, especially with ROCm. > * Use `--security-opt seccomp=unconfined` to avoid seccomp sandbox issues (needed for some GPU syscalls). +#### 2.1.1 Updating boxes + +If you want to make sure to get updated version of the toolboxes, always pull the new image and delete any existing box: + +```sh +podman pull docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan-amdvlk +toolbox rm -f llama-vulkan-amdvlk +``` + ### 2.2 Running models inside the toolboxes Before running any commands, you must first enter your toolbox container shell using: