Brandon T. Nguyen :v_bi:<p>Got <a href="https://transfem.social/tags/Proxmox" rel="nofollow noopener noreferrer" target="_blank">#Proxmox</a> installed on the <a href="https://transfem.social/tags/Supermicro" rel="nofollow noopener noreferrer" target="_blank">#Supermicro</a> SuperServer 4028GR-TRT2 and added to the cluster. I'm being mad janky with my <a href="https://transfem.social/tags/corosync" rel="nofollow noopener noreferrer" target="_blank">#corosync</a> tho because cause I don't want the <a href="https://transfem.social/tags/GPU" rel="nofollow noopener noreferrer" target="_blank">#GPU</a> node to be a 24/7 machine so I gave my main three high availability nodes two <a href="https://transfem.social/tags/quorum" rel="nofollow noopener noreferrer" target="_blank">#quorum</a><span> votes instead of one so as long as the three nodes primary HA nodes are online, it can tolerate a single node failure. Next step is to install the nVidia drives, get the vGPU unlock working for some VDI LAN party fun, and then deploy a LXC with the GPUs passed-through and install llama.cpp<br><br></span><a href="https://transfem.social/tags/homelab" rel="nofollow noopener noreferrer" target="_blank">#homelab</a> <a href="https://transfem.social/tags/llm" rel="nofollow noopener noreferrer" target="_blank">#llm</a> <a href="https://transfem.social/tags/llama" rel="nofollow noopener noreferrer" target="_blank">#llama</a><span><br><br>RE: </span><a href="https://transfem.social/notes/a1v9w5kz0h7l01de" rel="nofollow noopener noreferrer" target="_blank">https://transfem.social/notes/a1v9w5kz0h7l01de</a></p>