Files
Wang, Kai Lawrence 5362321d3a Fix vllm model cache directory (#1642)
Signed-off-by: Wang, Kai Lawrence <kai.lawrence.wang@intel.com>
2025-03-10 13:40:42 +08:00

97 lines
2.9 KiB
YAML

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
services:
vllm-service:
image: ${REGISTRY:-opea}/vllm:${TAG:-latest}
container_name: codetrans-xeon-vllm-service
ports:
- "8008:80"
volumes:
- "${MODEL_CACHE:-./data}:/root/.cache/huggingface/hub"
shm_size: 1g
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LLM_MODEL_ID: ${LLM_MODEL_ID}
VLLM_TORCH_PROFILER_DIR: "/mnt"
healthcheck:
test: ["CMD-SHELL", "curl -f http://$host_ip:8008/health || exit 1"]
interval: 10s
timeout: 10s
retries: 100
command: --model $LLM_MODEL_ID --host 0.0.0.0 --port 80
llm:
image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest}
container_name: codetrans-xeon-llm-server
depends_on:
vllm-service:
condition: service_healthy
ports:
- "9000:9000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
LLM_COMPONENT_NAME: ${LLM_COMPONENT_NAME}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
codetrans-xeon-backend-server:
image: ${REGISTRY:-opea}/codetrans:${TAG:-latest}
container_name: codetrans-xeon-backend-server
depends_on:
- vllm-service
- llm
ports:
- "${BACKEND_SERVICE_PORT:-7777}:7777"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
- LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
ipc: host
restart: always
codetrans-xeon-ui-server:
image: ${REGISTRY:-opea}/codetrans-ui:${TAG:-latest}
container_name: codetrans-xeon-ui-server
depends_on:
- codetrans-xeon-backend-server
ports:
- "${FRONTEND_SERVICE_PORT:-5173}:5173"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- BASE_URL=${BACKEND_SERVICE_ENDPOINT}
ipc: host
restart: always
codetrans-xeon-nginx-server:
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
container_name: codetrans-xeon-nginx-server
depends_on:
- codetrans-xeon-backend-server
- codetrans-xeon-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