A practical guide to running multiple Qwen3 models through a single llama-server instance using model routing. Covers embedding, reranking, and chat/vision models.
Tested on Windows with RTX 3090 (24GB VRAM), llama-server build from llama.cpp master branch. Last updated: 2025-03-09.
| name | description |
|---|---|
orchestrating-swarms |
Master multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns. |
Master multi-agent orchestration using Claude Code's TeammateTool and Task system.
| """ | |
| The most atomic way to train and run inference for a GPT in pure, dependency-free Python. | |
| This file is the complete algorithm. | |
| Everything else is just efficiency. | |
| @karpathy | |
| """ | |
| import os # os.path.exists | |
| import math # math.log, math.exp |
| 8 Eyes (U) [!].nes | |
| Abadox (J).nes | |
| Addams Family, The (E) [!].nes | |
| Adventures in the Magic Kingdom (E) [!].nes | |
| Adventures of Lolo (U) [!].nes | |
| Aladdin 4 (1996) (Unl) [!].nes | |
| Alien 3 (E) [!].nes | |
| Alien Syndrome (J).nes | |
| Antarctic Adventure (J).nes | |
| Astyanax (U) [!].nes |
| """ | |
| The most atomic way to train and run inference for a GPT in pure, dependency-free Python. | |
| This file is the complete algorithm. | |
| Everything else is just efficiency. | |
| @karpathy | |
| """ | |
| import os # os.path.exists | |
| import math # math.log, math.exp |
Source: https://www.leowkahman.com/2016/03/19/disable-ipv6-raspberry-raspbian/
Firstly, check for presence of IPv6 using ifconfig. You should be seeing a few lines containing inet6 addr: ....
To disable, edit a file: sudo nano /etc/sysctl.conf
Add the following line:
net.ipv6.conf.all.disable_ipv6 = 1
This guide covers the complete setup of KVM (Kernel-based Virtual Machine) with QEMU and libvirt on Ubuntu 24.04 LTS. KVM provides near-native performance virtualization on Linux systems and is ideal for homelab environments.
