83 lines
1.9 KiB
YAML
83 lines
1.9 KiB
YAML
version: '3.3'
|
|
|
|
services:
|
|
init:
|
|
image: tabbyml/tabby
|
|
container_name: tabby-init
|
|
command: dagu start --params=MODEL_NAME=${MODEL_NAME} ./tabby/tasks/init.yaml
|
|
volumes:
|
|
- ${HF_VOLUME}
|
|
|
|
server:
|
|
image: tabbyml/tabby
|
|
container_name: tabby-server
|
|
command: uvicorn tabby.server:app --host 0.0.0.0 --port 5000
|
|
environment:
|
|
MODEL_NAME: ${MODEL_NAME}
|
|
MODEL_BACKEND: triton
|
|
EVENTS_LOG_DIR: /logs/tabby-server
|
|
ports:
|
|
- "5000:5000"
|
|
volumes:
|
|
- ${HF_VOLUME}
|
|
- ${LOGS_VOLUME}
|
|
depends_on:
|
|
init:
|
|
condition: service_completed_successfully
|
|
triton:
|
|
condition: service_healthy
|
|
|
|
admin:
|
|
image: tabbyml/tabby
|
|
container_name: tabby-admin
|
|
command: streamlit run tabby/admin/Home.py
|
|
ports:
|
|
- "8501:8501"
|
|
volumes:
|
|
- ${LOGS_VOLUME}
|
|
|
|
triton:
|
|
image: tabbyml/fastertransformer_backend
|
|
container_name: tabby-triton
|
|
command: /scripts/triton.sh
|
|
shm_size: 1gb
|
|
volumes:
|
|
- ./scripts:/scripts
|
|
- ${HF_VOLUME}
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
environment:
|
|
MODEL_NAME: ${MODEL_NAME}
|
|
depends_on:
|
|
init:
|
|
condition: service_completed_successfully
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:8002/metrics"]
|
|
interval: 2s
|
|
timeout: 2s
|
|
start_period: 120s
|
|
|
|
vector:
|
|
image: timberio/vector:0.28.1-alpine
|
|
container_name: tabby-vector
|
|
volumes:
|
|
- ./config/vector.toml:/etc/vector/vector.toml:ro
|
|
- ${LOGS_VOLUME}
|
|
|
|
dagu:
|
|
image: tabbyml/tabby
|
|
container_name: tabby-dagu
|
|
command: dagu scheduler
|
|
volumes:
|
|
- ${LOGS_VOLUME}
|
|
environment:
|
|
DAGU_DAGS: tabby/tasks
|
|
depends_on:
|
|
init:
|
|
condition: service_completed_successfully
|