[Unit]
Description=A Llama CPP Server For Embedding Models

[Container]
# Shared AI internal pod
Pod=ai-internal.pod

# Image is built locally via podman build
Image=localhost/llama-cpp-vulkan:latest

# Downloaded models volume
Volume=/home/ai/models/embedding:/models:z

# GPU Device
AddDevice=/dev/kfd
AddDevice=/dev/dri

# Server command
Exec=--port 8001 \
    -c 0 \
    --perf \
    --n-gpu-layers all \
    --models-max 1 \
    --models-dir /models \
    --embedding \
    -m /models/qwen3-embed-4b/Qwen3-Embedding-4B-Q8_0.gguf \
    --alias embed

# Health Check
HealthCmd=CMD-SHELL curl --fail http://127.0.0.1:8001/props || exit 1
HealthInterval=10s
HealthRetries=3
HealthStartPeriod=10s
HealthTimeout=30s
HealthOnFailure=kill

[Service]
Restart=always
# Extend Timeout to allow time to pull the image
TimeoutStartSec=900

[Install]
# Start by default on boot
WantedBy=multi-user.target default.target