kusanagi: constrain ollama resources

laguna-xs-2.1 is large enough to nearly fill the workstation's display GPU at the previous 64k context and 1h keep-alive. That let Ollama keep a very large resident set around after requests and could destabilize the no-swap desktop session.

Unload models quicker, limit parallelism/queueing, reserve VRAM for the compositor, and cap the service cgroup so runaway requests fail before the desktop does.

Assisted-by: pi:gpt-5.5

0 files changed, 0 insertions, 0 deletions