95 lines
3.0 KiB
YAML
95 lines
3.0 KiB
YAML
# Copyright (C) 2024 Intel Corporation
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
services:
|
|
server:
|
|
image: ${REGISTRY:-opea}/edgecraftrag-server:${TAG:-latest}
|
|
container_name: edgecraftrag-server
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
HF_ENDPOINT: ${HF_ENDPOINT}
|
|
vLLM_ENDPOINT: ${vLLM_ENDPOINT}
|
|
ENABLE_BENCHMARK: ${ENABLE_BENCHMARK:-false}
|
|
volumes:
|
|
- ${MODEL_PATH:-${PWD}}:/home/user/models
|
|
- ${DOC_PATH:-${PWD}}:/home/user/docs
|
|
- ${GRADIO_PATH:-${PWD}}:/home/user/gradio_cache
|
|
- ${HF_CACHE:-${HOME}/.cache}:/home/user/.cache
|
|
- ${PROMPT_PATH:-${PWD}}:/templates/custom
|
|
ports:
|
|
- ${PIPELINE_SERVICE_PORT:-16010}:${PIPELINE_SERVICE_PORT:-16010}
|
|
devices:
|
|
- /dev/dri:/dev/dri
|
|
group_add:
|
|
- ${VIDEOGROUPID:-44}
|
|
- ${RENDERGROUPID:-109}
|
|
ecrag:
|
|
image: ${REGISTRY:-opea}/edgecraftrag:${TAG:-latest}
|
|
container_name: edgecraftrag
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
MEGA_SERVICE_PORT: ${MEGA_SERVICE_PORT:-16011}
|
|
MEGA_SERVICE_HOST_IP: ${MEGA_SERVICE_HOST_IP:-${HOST_IP}}
|
|
PIPELINE_SERVICE_PORT: ${PIPELINE_SERVICE_PORT:-16010}
|
|
PIPELINE_SERVICE_HOST_IP: ${PIPELINE_SERVICE_HOST_IP:-${HOST_IP}}
|
|
ports:
|
|
- ${MEGA_SERVICE_PORT:-16011}:${MEGA_SERVICE_PORT:-16011}
|
|
depends_on:
|
|
- server
|
|
ui:
|
|
image: ${REGISTRY:-opea}/edgecraftrag-ui:${TAG:-latest}
|
|
container_name: edgecraftrag-ui
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
MEGA_SERVICE_PORT: ${MEGA_SERVICE_PORT:-16011}
|
|
MEGA_SERVICE_HOST_IP: ${MEGA_SERVICE_HOST_IP:-${HOST_IP}}
|
|
PIPELINE_SERVICE_PORT: ${PIPELINE_SERVICE_PORT:-16010}
|
|
PIPELINE_SERVICE_HOST_IP: ${PIPELINE_SERVICE_HOST_IP:-${HOST_IP}}
|
|
UI_SERVICE_PORT: ${UI_SERVICE_PORT:-8082}
|
|
UI_SERVICE_HOST_IP: ${UI_SERVICE_HOST_IP:-0.0.0.0}
|
|
volumes:
|
|
- ${GRADIO_PATH:-${PWD}}:/home/user/gradio_cache
|
|
ports:
|
|
- ${UI_SERVICE_PORT:-8082}:${UI_SERVICE_PORT:-8082}
|
|
restart: always
|
|
depends_on:
|
|
- server
|
|
- ecrag
|
|
vllm-openvino-server:
|
|
container_name: vllm-openvino-server
|
|
image: opea/vllm-arc:latest
|
|
ports:
|
|
- ${VLLM_SERVICE_PORT:-8008}:80
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
VLLM_OPENVINO_DEVICE: GPU
|
|
HF_ENDPOINT: ${HF_ENDPOINT}
|
|
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
|
|
volumes:
|
|
- ${HF_CACHE:-${HOME}/.cache}:/root/.cache
|
|
devices:
|
|
- /dev/dri
|
|
group_add:
|
|
- ${VIDEOGROUPID:-44}
|
|
- ${RENDERGROUPID:-109}
|
|
entrypoint: /bin/bash -c "\
|
|
cd / && \
|
|
export VLLM_CPU_KVCACHE_SPACE=50 && \
|
|
export VLLM_OPENVINO_ENABLE_QUANTIZED_WEIGHTS=ON && \
|
|
python3 -m vllm.entrypoints.openai.api_server \
|
|
--model '${LLM_MODEL}' \
|
|
--max_model_len=4096 \
|
|
--host 0.0.0.0 \
|
|
--port 80"
|
|
networks:
|
|
default:
|
|
driver: bridge
|