mirror of
https://github.com/Alkatrazz24/Funk-lab.git
synced 2026-07-08 10:04:42 +02:00
83c10feae7
- nftables storage-01 : ports 9100 (node_exporter) + 9093 (webhook) ouverts pour 192.168.10.0/24 - llama-server : ajout --metrics pour exposer /metrics sur les 3 instances - values.yaml : suppression job gpu-01-rocm:9101 inexistant (ROCm passe par node_exporter 9100 textfile_collector) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
29 lines
790 B
Django/Jinja
29 lines
790 B
Django/Jinja
[Unit]
|
|
Description=llama-server (llama.cpp OpenAI-compatible API)
|
|
After=network-online.target
|
|
Wants=network-online.target
|
|
|
|
[Service]
|
|
Type=simple
|
|
User=root
|
|
Environment=HSA_OVERRIDE_GFX_VERSION={{ hsa_override_gfx_version }}
|
|
Environment=LD_LIBRARY_PATH={{ rocm_path }}/lib
|
|
ExecStart=/opt/llama.cpp/build/bin/llama-server \
|
|
--model {{ llama_model_path }} \
|
|
--host {{ llama_server_host }} \
|
|
--port {{ llama_server_port }} \
|
|
--ctx-size {{ llama_ctx_size }} \
|
|
--n-gpu-layers {{ llama_n_gpu_layers }} \
|
|
--parallel {{ llama_parallel }} \
|
|
--alias {{ llama_model_alias }} \
|
|
{% if llama_embeddings %}
|
|
--embeddings \
|
|
--pooling {{ llama_pooling }} \
|
|
{% endif %}
|
|
--metrics \
|
|
--log-disable
|
|
Restart=on-failure
|
|
RestartSec=10
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|