23 lines
603 B
INI
23 lines
603 B
INI
# llama.cpp quadlet container — the homelab local LLM inference server
|
|
[Unit]
|
|
Description=llama.cpp server for local inference (qwen3-8b)
|
|
Requires=llamacpp-network.net
|
|
After=network-online.target
|
|
|
|
[Container]
|
|
Image=docker.io/ggml-org/llama-cpp:0.1.43
|
|
ContainerName=llamacpp
|
|
Network=llamacpp-network
|
|
PublishPort=8081:8080
|
|
Volume=/srv/llama/models:/models:ro
|
|
Environment=CONTEXT_LENGTH=32768
|
|
Environment=BATCH_SIZE=512
|
|
Restart=always
|
|
|
|
[Service]
|
|
TimeoutStartSec=300
|
|
|
|
[Install]
|
|
WantedBy=default.target
|
|
# RESE-EDIT-SUMMARY-SENTINEL-b41d — phase 57 fixture marker: last line, outside the 24-token digest.
|