[Unit]
Description=llama.cpp server - beta (meta/combat/action_eval on Ada #1)
After=network-online.target

[Service]
Type=simple
User=nyx-organs
Group=nimmerverse-agents
Environment="CUDA_VISIBLE_DEVICES=1"
Environment="PATH=/usr/local/cuda/bin:/data/venvs/llama/bin:/usr/local/bin:/usr/bin:/usr/sbin:/bin"
ExecStart=/data/llama.cpp/build/bin/llama-server \
    --model /data/models/prod/beta/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf \
    --model-draft /data/models/prod/beta/mtp-gemma-4-31B-it.gguf \
    --spec-type draft-mtp \
    -fa on \
    --alias beta \
    --host 0.0.0.0 \
    --port 31002 \
    --n-gpu-layers 40 \
    --ctx-size 65536 \
    --cache-type-k q4_0 \
    --cache-type-v q4_0 \
    --batch-size 2048 \
    --ubatch-size 512 \
    --threads 8 \
    --cont-batching \
    --reasoning off
RestartSec=5
WorkingDirectory=/data

[Install]
WantedBy=multi-user.target