107 lines
3.4 KiB
YAML
107 lines
3.4 KiB
YAML
# Copyright (C) 2024 Intel Corporation
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
services:
|
|
vllm-gaudi-service:
|
|
image: ${REGISTRY:-opea}/vllm-gaudi:${TAG:-latest}
|
|
container_name: vllm-gaudi-service
|
|
ports:
|
|
- ${VLLM_PORT:-8399}:80
|
|
volumes:
|
|
- "./data:/root/.cache/huggingface/hub"
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
|
|
HABANA_VISIBLE_DEVICES: all
|
|
OMPI_MCA_btl_vader_single_copy_mechanism: none
|
|
LLM_MODEL_ID: ${LVM_MODEL_ID}
|
|
VLLM_TORCH_PROFILER_DIR: "/mnt"
|
|
VLLM_SKIP_WARMUP: ${VLLM_SKIP_WARMUP:-false}
|
|
MAX_MODEL_LEN: ${MAX_TOTAL_TOKENS:-4096}
|
|
MAX_SEQ_LEN_TO_CAPTURE: ${MAX_TOTAL_TOKENS:-4096}
|
|
PT_HPUGRAPH_DISABLE_TENSOR_CACHE: false # https://github.com/HabanaAI/vllm-fork/issues/841#issuecomment-2700421704
|
|
runtime: habana
|
|
cap_add:
|
|
- SYS_NICE
|
|
ipc: host
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
|
|
interval: 10s
|
|
timeout: 10s
|
|
retries: 150
|
|
command: --model $LVM_MODEL_ID --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --chat-template examples/template_llava.jinja # https://docs.vllm.ai/en/v0.5.0/models/vlm.html
|
|
lvm:
|
|
image: ${REGISTRY:-opea}/lvm:${TAG:-latest}
|
|
container_name: lvm-vllm-gaudi-service
|
|
depends_on:
|
|
vllm-gaudi-service:
|
|
condition: service_healthy
|
|
ports:
|
|
- "9399:9399"
|
|
ipc: host
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
LVM_ENDPOINT: ${LVM_ENDPOINT}
|
|
LVM_COMPONENT_NAME: "OPEA_VLLM_LVM"
|
|
LLM_MODEL_ID: ${LVM_MODEL_ID}
|
|
HF_HUB_DISABLE_PROGRESS_BARS: 1
|
|
HF_HUB_ENABLE_HF_TRANSFER: 0
|
|
restart: unless-stopped
|
|
visualqna-gaudi-backend-server:
|
|
image: ${REGISTRY:-opea}/visualqna:${TAG:-latest}
|
|
container_name: visualqna-gaudi-backend-server
|
|
depends_on:
|
|
- vllm-gaudi-service
|
|
- lvm
|
|
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-gaudi-ui-server:
|
|
image: ${REGISTRY:-opea}/visualqna-ui:${TAG:-latest}
|
|
container_name: visualqna-gaudi-ui-server
|
|
depends_on:
|
|
- visualqna-gaudi-backend-server
|
|
ports:
|
|
- "5173:5173"
|
|
environment:
|
|
- no_proxy=${no_proxy}
|
|
- https_proxy=${https_proxy}
|
|
- http_proxy=${http_proxy}
|
|
- BACKEND_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
|
|
ipc: host
|
|
restart: always
|
|
visualqna-gaudi-nginx-server:
|
|
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
|
|
container_name: visualqna-gaudi-nginx-server
|
|
depends_on:
|
|
- visualqna-gaudi-backend-server
|
|
- visualqna-gaudi-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
|