dynamo/examples/diffusers/local/docker-compose.yml

124 lines
3.0 KiB
YAML

# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
# Worker count is controlled by COMPOSE_PROFILES (1-8).
# COMPOSE_PROFILES=4 starts backend-0..backend-3 on GPUs 0..3.
x-backend-base: &backend-base
build:
context: ..
dockerfile: Dockerfile
image: dynamo-fastvideo-diffusers:latest
restart: on-failure
command: python worker.py
environment:
- DYN_DISCOVERY_BACKEND=file
- DYN_FILE_KV=/tmp/dynamo-discovery
- LD_LIBRARY_PATH=
- TORCHINDUCTOR_CACHE_DIR=/cache/torchinductor
- TRITON_CACHE_DIR=/cache/triton
volumes:
- dynamo-discovery:/tmp/dynamo-discovery
- huggingface-cache:/root/.cache/huggingface
ipc: host
shm_size: 8g
ulimits:
memlock: -1
stack: 67108864
depends_on:
- frontend
services:
frontend:
build:
context: ..
dockerfile: Dockerfile
image: dynamo-fastvideo-diffusers:latest
restart: on-failure
command: >
python -m dynamo.frontend
--http-port 8000
--discovery-backend file
environment:
- DYN_FILE_KV=/tmp/dynamo-discovery
volumes:
- dynamo-discovery:/tmp/dynamo-discovery
ports:
- "8000:8000"
backend-0:
<<: *backend-base
profiles: ["1", "2", "3", "4", "5", "6", "7", "8"]
deploy:
resources:
reservations:
devices:
- { driver: nvidia, device_ids: ["0"], capabilities: [gpu] }
backend-1:
<<: *backend-base
profiles: ["2", "3", "4", "5", "6", "7", "8"]
deploy:
resources:
reservations:
devices:
- { driver: nvidia, device_ids: ["1"], capabilities: [gpu] }
backend-2:
<<: *backend-base
profiles: ["3", "4", "5", "6", "7", "8"]
deploy:
resources:
reservations:
devices:
- { driver: nvidia, device_ids: ["2"], capabilities: [gpu] }
backend-3:
<<: *backend-base
profiles: ["4", "5", "6", "7", "8"]
deploy:
resources:
reservations:
devices:
- { driver: nvidia, device_ids: ["3"], capabilities: [gpu] }
backend-4:
<<: *backend-base
profiles: ["5", "6", "7", "8"]
deploy:
resources:
reservations:
devices:
- { driver: nvidia, device_ids: ["4"], capabilities: [gpu] }
backend-5:
<<: *backend-base
profiles: ["6", "7", "8"]
deploy:
resources:
reservations:
devices:
- { driver: nvidia, device_ids: ["5"], capabilities: [gpu] }
backend-6:
<<: *backend-base
profiles: ["7", "8"]
deploy:
resources:
reservations:
devices:
- { driver: nvidia, device_ids: ["6"], capabilities: [gpu] }
backend-7:
<<: *backend-base
profiles: ["8"]
deploy:
resources:
reservations:
devices:
- { driver: nvidia, device_ids: ["7"], capabilities: [gpu] }
volumes:
dynamo-discovery:
huggingface-cache: