993688ac91
- Changed the external port of llava-tgi-service from 9399 to 8399 - This resolves the port conflict with the lvm-tgi service - Internal port mapping remains unchanged (80)
70 lines
1.9 KiB
YAML
70 lines
1.9 KiB
YAML
# Copyright (C) 2024 Intel Corporation
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
services:
|
|
llava-tgi-service:
|
|
image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
|
|
container_name: tgi-llava-xeon-server
|
|
ports:
|
|
- "8399:80"
|
|
volumes:
|
|
- "./data:/data"
|
|
shm_size: 1g
|
|
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
|
|
command: --model-id ${LVM_MODEL_ID} --max-input-length 4096 --max-total-tokens 8192 --cuda-graphs 0
|
|
lvm-tgi:
|
|
image: ${REGISTRY:-opea}/lvm-tgi:${TAG:-latest}
|
|
container_name: lvm-tgi-server
|
|
depends_on:
|
|
- llava-tgi-service
|
|
ports:
|
|
- "9399:9399"
|
|
ipc: host
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
LVM_ENDPOINT: ${LVM_ENDPOINT}
|
|
HF_HUB_DISABLE_PROGRESS_BARS: 1
|
|
HF_HUB_ENABLE_HF_TRANSFER: 0
|
|
restart: unless-stopped
|
|
visualqna-xeon-backend-server:
|
|
image: ${REGISTRY:-opea}/visualqna:${TAG:-latest}
|
|
container_name: visualqna-xeon-backend-server
|
|
depends_on:
|
|
- llava-tgi-service
|
|
- lvm-tgi
|
|
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-xeon-ui-server:
|
|
image: ${REGISTRY:-opea}/visualqna-ui:${TAG:-latest}
|
|
container_name: visualqna-xeon-ui-server
|
|
depends_on:
|
|
- visualqna-xeon-backend-server
|
|
ports:
|
|
- "5173:5173"
|
|
environment:
|
|
- no_proxy=${no_proxy}
|
|
- https_proxy=${https_proxy}
|
|
- http_proxy=${http_proxy}
|
|
- CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
|
|
ipc: host
|
|
restart: always
|
|
|
|
networks:
|
|
default:
|
|
driver: bridge
|