106 lines
3.2 KiB
YAML
106 lines
3.2 KiB
YAML
# Copyright (C) 2024 Advanced Micro Devices, Inc.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
services:
|
|
visualqna-vllm-service:
|
|
image: ${REGISTRY:-opea}/vllm-rocm:${TAG:-latest}
|
|
container_name: visualqna-vllm-service
|
|
ports:
|
|
- "${VISUALQNA_VLLM_SERVICE_PORT:-8081}:8011"
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
HUGGINGFACEHUB_API_TOKEN: ${VISUALQNA_HUGGINGFACEHUB_API_TOKEN}
|
|
HF_TOKEN: ${VISUALQNA_HUGGINGFACEHUB_API_TOKEN}
|
|
HF_HUB_DISABLE_PROGRESS_BARS: 1
|
|
HF_HUB_ENABLE_HF_TRANSFER: 0
|
|
WILM_USE_TRITON_FLASH_ATTENTION: 0
|
|
PYTORCH_JIT: 0
|
|
volumes:
|
|
- "${MODEL_CACHE:-./data}:/data"
|
|
shm_size: 20G
|
|
devices:
|
|
- /dev/kfd:/dev/kfd
|
|
- /dev/dri/:/dev/dri/
|
|
cap_add:
|
|
- SYS_PTRACE
|
|
group_add:
|
|
- video
|
|
security_opt:
|
|
- seccomp:unconfined
|
|
- apparmor=unconfined
|
|
command: "--model ${VISUALQNA_LVM_MODEL_ID} --swap-space 16 --disable-log-requests --dtype float16 --tensor-parallel-size 1 --host 0.0.0.0 --port 8011 --num-scheduler-steps 1 --distributed-executor-backend \"mp\""
|
|
ipc: host
|
|
lvm:
|
|
image: ${REGISTRY:-opea}/lvm:${TAG:-latest}
|
|
container_name: lvm-server
|
|
depends_on:
|
|
- visualqna-vllm-service
|
|
ports:
|
|
- "9399:9399"
|
|
ipc: host
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
LVM_COMPONENT_NAME: "OPEA_VLLM_LVM"
|
|
LVM_ENDPOINT: ${LVM_ENDPOINT}
|
|
LLM_MODEL_ID: ${VISUALQNA_LVM_MODEL_ID}
|
|
HF_HUB_DISABLE_PROGRESS_BARS: 1
|
|
HF_HUB_ENABLE_HF_TRANSFER: 0
|
|
restart: unless-stopped
|
|
visualqna-rocm-backend-server:
|
|
image: ${REGISTRY:-opea}/visualqna:${TAG:-latest}
|
|
container_name: visualqna-rocm-backend-server
|
|
depends_on:
|
|
- visualqna-vllm-service
|
|
- lvm
|
|
ports:
|
|
- "${BACKEND_SERVICE_PORT:-8888}:8888"
|
|
environment:
|
|
- no_proxy=${no_proxy}
|
|
- https_proxy=${https_proxy}
|
|
- http_proxy=${http_proxy}
|
|
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
|
|
- LVM_SERVICE_HOST_IP=${LVM_SERVICE_HOST_IP}
|
|
ipc: host
|
|
restart: always
|
|
visualqna-rocm-ui-server:
|
|
image: ${REGISTRY:-opea}/visualqna-ui:${TAG:-latest}
|
|
container_name: visualqna-rocm-ui-server
|
|
depends_on:
|
|
- visualqna-rocm-backend-server
|
|
ports:
|
|
- "${FRONTEND_SERVICE_PORT:-5173}:5173"
|
|
environment:
|
|
- no_proxy=${no_proxy}
|
|
- https_proxy=${https_proxy}
|
|
- http_proxy=${http_proxy}
|
|
- BACKEND_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
|
|
ipc: host
|
|
restart: always
|
|
visualqna-nginx-server:
|
|
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
|
|
container_name: visualqna-rocm-nginx-server
|
|
depends_on:
|
|
- visualqna-rocm-backend-server
|
|
- visualqna-rocm-ui-server
|
|
ports:
|
|
- "${NGINX_PORT:-80}:80"
|
|
environment:
|
|
- no_proxy=${no_proxy}
|
|
- https_proxy=${https_proxy}
|
|
- http_proxy=${http_proxy}
|
|
- FRONTEND_SERVICE_IP=${HOST_IP}
|
|
- FRONTEND_SERVICE_PORT=${FRONTEND_SERVICE_PORT}
|
|
- BACKEND_SERVICE_NAME=${BACKEND_SERVICE_NAME}
|
|
- BACKEND_SERVICE_IP=${HOST_IP}
|
|
- BACKEND_SERVICE_PORT=${BACKEND_SERVICE_PORT}
|
|
ipc: host
|
|
restart: always
|
|
|
|
networks:
|
|
default:
|
|
driver: bridge
|