112 lines
3.3 KiB
YAML
112 lines
3.3 KiB
YAML
# Copyright (C) 2024 Advanced Micro Devices, Inc.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
services:
|
|
docsum-vllm-service:
|
|
image: ${REGISTRY:-opea}/vllm-rocm:${TAG:-latest}
|
|
container_name: docsum-vllm-service
|
|
ports:
|
|
- "${DOCSUM_VLLM_SERVICE_PORT:-8081}:8011"
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
HUGGINGFACEHUB_API_TOKEN: ${DOCSUM_HUGGINGFACEHUB_API_TOKEN}
|
|
HF_TOKEN: ${DOCSUM_HUGGINGFACEHUB_API_TOKEN}
|
|
HF_HUB_DISABLE_PROGRESS_BARS: 1
|
|
HF_HUB_ENABLE_HF_TRANSFER: 0
|
|
VLLM_USE_TRITON_FLASH_ATTENTION: 0
|
|
PYTORCH_JIT: 0
|
|
healthcheck:
|
|
test: [ "CMD-SHELL", "curl -f http://${HOST_IP}:${DOCSUM_VLLM_SERVICE_PORT:-8081}/health || exit 1" ]
|
|
interval: 10s
|
|
timeout: 10s
|
|
retries: 100
|
|
volumes:
|
|
- "${MODEL_CACHE:-./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 ${DOCSUM_LLM_MODEL_ID} --swap-space 16 --disable-log-requests --dtype float16 --tensor-parallel-size 4 --host 0.0.0.0 --port 8011 --num-scheduler-steps 1 --distributed-executor-backend \"mp\""
|
|
ipc: host
|
|
|
|
docsum-llm-server:
|
|
image: ${REGISTRY:-opea}/llm-docsum:${TAG:-latest}
|
|
container_name: docsum-llm-server
|
|
depends_on:
|
|
docsum-vllm-service:
|
|
condition: service_healthy
|
|
ports:
|
|
- "${DOCSUM_LLM_SERVER_PORT}:9000"
|
|
ipc: host
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
LLM_ENDPOINT: ${DOCSUM_LLM_ENDPOINT}
|
|
HUGGINGFACEHUB_API_TOKEN: ${DOCSUM_HUGGINGFACEHUB_API_TOKEN}
|
|
MAX_INPUT_TOKENS: ${DOCSUM_MAX_INPUT_TOKENS}
|
|
MAX_TOTAL_TOKENS: ${DOCSUM_MAX_TOTAL_TOKENS}
|
|
LLM_MODEL_ID: ${DOCSUM_LLM_MODEL_ID}
|
|
DocSum_COMPONENT_NAME: "OpeaDocSumvLLM"
|
|
LOGFLAG: ${LOGFLAG:-False}
|
|
restart: unless-stopped
|
|
|
|
whisper:
|
|
image: ${REGISTRY:-opea}/whisper:${TAG:-latest}
|
|
container_name: whisper-service
|
|
ports:
|
|
- "${DOCSUM_WHISPER_PORT:-7066}:7066"
|
|
ipc: host
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
restart: unless-stopped
|
|
|
|
docsum-backend-server:
|
|
image: ${REGISTRY:-opea}/docsum:${TAG:-latest}
|
|
container_name: docsum-backend-server
|
|
depends_on:
|
|
- docsum-vllm-service
|
|
- docsum-llm-server
|
|
ports:
|
|
- "${DOCSUM_BACKEND_SERVER_PORT}:8888"
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
https_proxy: ${https_proxy}
|
|
http_proxy: ${http_proxy}
|
|
MEGA_SERVICE_HOST_IP: ${HOST_IP}
|
|
LLM_SERVICE_HOST_IP: ${HOST_IP}
|
|
ASR_SERVICE_HOST_IP: ${ASR_SERVICE_HOST_IP}
|
|
ipc: host
|
|
restart: always
|
|
|
|
docsum-gradio-ui:
|
|
image: ${REGISTRY:-opea}/docsum-gradio-ui:${TAG:-latest}
|
|
container_name: docsum-ui-server
|
|
depends_on:
|
|
- docsum-backend-server
|
|
ports:
|
|
- "${DOCSUM_FRONTEND_PORT:-5173}:5173"
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
https_proxy: ${https_proxy}
|
|
http_proxy: ${http_proxy}
|
|
BACKEND_SERVICE_ENDPOINT: ${BACKEND_SERVICE_ENDPOINT}
|
|
DOC_BASE_URL: ${BACKEND_SERVICE_ENDPOINT}
|
|
ipc: host
|
|
restart: always
|
|
|
|
networks:
|
|
default:
|
|
driver: bridge
|