42 lines
840 B
YAML
42 lines
840 B
YAML
version: '3.3'
|
|
|
|
services:
|
|
init:
|
|
image: tabbyml/tabby
|
|
container_name: init
|
|
user: root
|
|
volumes:
|
|
- ${DATA_VOLUME}
|
|
- ${HF_VOLUME}
|
|
command: chown -R 1000 /data
|
|
|
|
tabby:
|
|
image: tabbyml/tabby
|
|
container_name: tabby
|
|
shm_size: 1gb
|
|
environment:
|
|
MODEL_NAME: ${MODEL_NAME}
|
|
MODEL_BACKEND: triton
|
|
MODEL_REPLICA: ${MODEL_REPLICA:-1}
|
|
ports:
|
|
- "5000:5000"
|
|
- "8080:8080"
|
|
- "8501:8501"
|
|
volumes:
|
|
- ${DATA_VOLUME}
|
|
- ${HF_VOLUME}
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:5000"]
|
|
interval: 2s
|
|
timeout: 2s
|
|
start_period: 1200s
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
depends_on:
|
|
- init
|