106 lines
3.1 KiB
YAML
106 lines
3.1 KiB
YAML
# Copyright (C) 2024 Intel Corporation
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
services:
|
|
llava-tgi-service:
|
|
image: ghcr.io/huggingface/tgi-gaudi:2.3.1
|
|
container_name: tgi-llava-gaudi-server
|
|
ports:
|
|
- "8399:80"
|
|
volumes:
|
|
- "${MODEL_CACHE:-./data}:/data"
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
HF_HUB_DISABLE_PROGRESS_BARS: 1
|
|
HF_HUB_ENABLE_HF_TRANSFER: 0
|
|
HABANA_VISIBLE_DEVICES: all
|
|
OMPI_MCA_btl_vader_single_copy_mechanism: none
|
|
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
|
|
ENABLE_HPU_GRAPH: true
|
|
LIMIT_HPU_GRAPH: true
|
|
USE_FLASH_ATTENTION: true
|
|
FLASH_ATTENTION_RECOMPUTE: true
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "curl -f http://$host_ip:8399/health || exit 1"]
|
|
interval: 10s
|
|
timeout: 10s
|
|
retries: 60
|
|
runtime: habana
|
|
cap_add:
|
|
- SYS_NICE
|
|
ipc: host
|
|
command: --model-id ${LVM_MODEL_ID} --max-input-length 4096 --max-total-tokens 8192
|
|
lvm:
|
|
image: ${REGISTRY:-opea}/lvm:${TAG:-latest}
|
|
container_name: lvm-gaudi-server
|
|
depends_on:
|
|
llava-tgi-service:
|
|
condition: service_healthy
|
|
ports:
|
|
- "9399:9399"
|
|
ipc: host
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
LVM_ENDPOINT: ${LVM_ENDPOINT}
|
|
LVM_COMPONENT_NAME: "OPEA_TGI_LLAVA_LVM"
|
|
HF_HUB_DISABLE_PROGRESS_BARS: 1
|
|
HF_HUB_ENABLE_HF_TRANSFER: 0
|
|
restart: unless-stopped
|
|
visualqna-gaudi-backend-server:
|
|
image: ${REGISTRY:-opea}/visualqna:${TAG:-latest}
|
|
container_name: visualqna-gaudi-backend-server
|
|
depends_on:
|
|
- llava-tgi-service
|
|
- lvm
|
|
ports:
|
|
- "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-gaudi-ui-server:
|
|
image: ${REGISTRY:-opea}/visualqna-ui:${TAG:-latest}
|
|
container_name: visualqna-gaudi-ui-server
|
|
depends_on:
|
|
- visualqna-gaudi-backend-server
|
|
ports:
|
|
- "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-gaudi-nginx-server:
|
|
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
|
|
container_name: visualqna-gaudi-nginx-server
|
|
depends_on:
|
|
- visualqna-gaudi-backend-server
|
|
- visualqna-gaudi-ui-server
|
|
ports:
|
|
- "${NGINX_PORT:-80}:80"
|
|
environment:
|
|
- no_proxy=${no_proxy}
|
|
- https_proxy=${https_proxy}
|
|
- http_proxy=${http_proxy}
|
|
- FRONTEND_SERVICE_IP=${FRONTEND_SERVICE_IP}
|
|
- FRONTEND_SERVICE_PORT=${FRONTEND_SERVICE_PORT}
|
|
- BACKEND_SERVICE_NAME=${BACKEND_SERVICE_NAME}
|
|
- BACKEND_SERVICE_IP=${BACKEND_SERVICE_IP}
|
|
- BACKEND_SERVICE_PORT=${BACKEND_SERVICE_PORT}
|
|
ipc: host
|
|
restart: always
|
|
|
|
networks:
|
|
default:
|
|
driver: bridge
|