Files
GenAIExamples/Translation/docker_compose/amd/gpu/rocm/compose_vllm.yaml
ZePan110 8d421b7912 [Translation] Integrate set_env.sh into test scripts. (#1785)
Signed-off-by: ZePan110 <ze.pan@intel.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
2025-04-11 09:31:40 +08:00

108 lines
3.6 KiB
YAML

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
services:
translation-vllm-service:
image: ${REGISTRY:-opea}/vllm-rocm:${TAG:-latest}
container_name: translation-vllm-service
ports:
- "${TRANSLATION_VLLM_SERVICE_PORT:-8081}:8011"
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGINGFACEHUB_API_TOKEN: ${TRANSLATION_HUGGINGFACEHUB_API_TOKEN}
HF_TOKEN: ${TRANSLATION_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:
- "./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 ${TRANSLATION_LLM_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
translation-llm:
image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest}
container_name: translation-llm-textgen-server
depends_on:
- translation-vllm-service
ports:
- "${TRANSLATION_LLM_PORT:-9000}:9000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${TRANSLATION_LLM_ENDPOINT}
LLM_MODEL_ID: ${TRANSLATION_LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${TRANSLATION_HUGGINGFACEHUB_API_TOKEN}
HF_TOKEN: ${TRANSLATION_HUGGINGFACEHUB_API_TOKEN}
LLM_COMPONENT_NAME: "OpeaTextGenService"
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
restart: unless-stopped
translation-backend-server:
image: ${REGISTRY:-opea}/translation:${TAG:-latest}
container_name: translation-backend-server
depends_on:
- translation-vllm-service
- translation-llm
ports:
- "${TRANSLATION_BACKEND_SERVICE_PORT:-8888}:8888"
environment:
no_proxy: ${no_proxy}
https_proxy: ${https_proxy}
http_proxy: ${http_proxy}
MEGA_SERVICE_HOST_IP: ${TRANSLATION_MEGA_SERVICE_HOST_IP}
LLM_SERVICE_HOST_IP: ${TRANSLATION_LLM_SERVICE_HOST_IP}
LLM_SERVICE_PORT: ${TRANSLATION_LLM_PORT}
ipc: host
restart: always
translation-ui-server:
image: ${REGISTRY:-opea}/translation-ui:${TAG:-latest}
container_name: translation-ui-server
depends_on:
- translation-backend-server
ports:
- "${TRANSLATION_FRONTEND_SERVICE_PORT:-5173}:5173"
environment:
no_proxy: ${no_proxy}
https_proxy: ${https_proxy}
http_proxy: ${http_proxy}
BASE_URL: ${TRANSLATION_BACKEND_SERVICE_ENDPOINT}
ipc: host
restart: always
translation-nginx-server:
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
container_name: translation-nginx-server
depends_on:
- translation-backend-server
- translation-ui-server
ports:
- "${TRANSLATION_NGINX_PORT:-80}:80"
environment:
no_proxy: ${no_proxy}
https_proxy: ${https_proxy}
http_proxy: ${http_proxy}
FRONTEND_SERVICE_IP: ${TRANSLATION_FRONTEND_SERVICE_IP}
FRONTEND_SERVICE_PORT: ${TRANSLATION_FRONTEND_SERVICE_PORT}
BACKEND_SERVICE_NAME: ${TRANSLATION_BACKEND_SERVICE_NAME}
BACKEND_SERVICE_IP: ${TRANSLATION_BACKEND_SERVICE_IP}
BACKEND_SERVICE_PORT: ${TRANSLATION_BACKEND_SERVICE_PORT}
ipc: host
restart: always
networks:
default:
driver: bridge