mirror of
https://github.com/Alkatrazz24/Funk-lab.git
synced 2026-07-08 08:54:42 +02:00
feat: initial commit — Ansible roles storage-01/gpu-01 opérationnels
This commit is contained in:
commit
b3fce8af5d
70 changed files with 2688 additions and 0 deletions
28
ansible/roles/llama_server/templates/llama-server.service.j2
Normal file
28
ansible/roles/llama_server/templates/llama-server.service.j2
Normal file
|
|
@ -0,0 +1,28 @@
|
|||
[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 %}
|
||||
--log-disable
|
||||
Restart=on-failure
|
||||
RestartSec=10
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
Loading…
Add table
Add a link
Reference in a new issue