tftsr_ai/templates/ollama/ollama-node0.service.j2

[Unit]
Description=Ollama Service — NUMA Node 0 (Coding Models)
After=network-online.target ollama.service
Wants=network-online.target

[Service]
ExecStart=/usr/bin/numactl --cpunodebind=0 {{ ollama_binary_path }} serve
Environment="OLLAMA_API_KEY={{ ollama_api_key }}"
Environment="OLLAMA_HOST=0.0.0.0:{{ ollama_node0_port }}"
Environment="OLLAMA_MODELS=/mnt/ai_data/ollama_models"
Environment="OLLAMA_KEEP_ALIVE={{ ollama_keep_alive }}"
Environment="OLLAMA_FLASH_ATTENTION={{ ollama_flash_attention }}"
Environment="OLLAMA_NUM_THREADS={{ ollama_num_threads }}"
Environment="OLLAMA_NUM_PARALLEL={{ ollama_num_parallel }}"
Environment="OLLAMA_MAX_LOADED_MODELS={{ ollama_max_loaded_models }}"
CPUAffinity={{ ollama_node0_cpu_affinity }}
LimitMEMLOCK=infinity
LimitNOFILE=65535
OOMScoreAdjust=-500
Restart=always
RestartSec=3
User=ollama
Group=ollama

[Install]
WantedBy=multi-user.target