#!/bin/bash
# Manual launcher for the NPU Qwen 3.5 9B llama-server backend.
# Used for ad-hoc testing; the systemd user unit
# llama-server-qwen35-npu.service is the production path.
set -e
ulimit -n 65536
exec /home/mfritsche/src/rk-llama.cpp/build/bin/llama-server \
  -m /home/mfritsche/models/Qwen3.5-9B-Q8_0.gguf \
  --alias qwen3.5-9b-npu \
  --reasoning off \
  -c 4096 -t 4 \
  --host 0.0.0.0 --port 8086