23 lines
772 B
YAML
23 lines
772 B
YAML
---
|
|
# Playbook: day3_deploy_qwen38_ctx131k.yml
|
|
# Purpose: Deploy Qwen3.8-27B-Q4_K_M ctx-size 65536 -> 131072 to astro-orbiter
|
|
# via llama-swap config re-render + restart.
|
|
#
|
|
# The git change to defaults/main.yml (line 235: ctx_size: 131072) is already staged.
|
|
# This playbook renders /etc/llama-swap/config.yaml from the updated defaults
|
|
# and restarts llama-swap to load the new ctx-size.
|
|
#
|
|
# Run:
|
|
# cd /home/hermes/git/homelab/ansible
|
|
# ansible-playbook -i inventory.yml playbooks/day3_deploy_qwen38_ctx131k.yml
|
|
#
|
|
- name: Deploy Qwen3.8 ctx-size 131072 to astro-orbiter
|
|
hosts: astro-orbiter
|
|
become: true
|
|
vars:
|
|
llm_swapmode_enabled: true
|
|
|
|
roles:
|
|
- role: llm-inference-multimodel
|
|
tags: [swapmode_config, swapmode_systemd, swapmode_verify]
|