Files
GenAIExamples/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml
chen, suyue 81b02bb947 Revert "HUGGINGFACEHUB_API_TOKEN environment is change to HF_TOKEN (#… (#1521)
Revert this PR since the test is not triggered properly due to the false merge of a WIP CI PR, 44a689b0bf, which block the CI test.

This change will be submitted in another PR.
2025-02-11 18:36:12 +08:00

115 lines
3.2 KiB
YAML

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
services:
tgi-gaudi-server:
image: ghcr.io/huggingface/tgi-gaudi:2.3.1
container_name: tgi-gaudi-server
ports:
- ${LLM_ENDPOINT_PORT:-8008}:80
volumes:
- "${DATA_PATH:-./data}:/data"
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
HABANA_VISIBLE_DEVICES: all
OMPI_MCA_btl_vader_single_copy_mechanism: none
ENABLE_HPU_GRAPH: true
LIMIT_HPU_GRAPH: true
USE_FLASH_ATTENTION: true
FLASH_ATTENTION_RECOMPUTE: true
host_ip: ${host_ip}
LLM_ENDPOINT_PORT: ${LLM_ENDPOINT_PORT}
runtime: habana
cap_add:
- SYS_NICE
ipc: host
healthcheck:
test: ["CMD-SHELL", "curl -f http://${host_ip}:${LLM_ENDPOINT_PORT}/health || exit 1"]
interval: 10s
timeout: 10s
retries: 100
command: --model-id ${LLM_MODEL_ID} --max-input-length ${MAX_INPUT_TOKENS} --max-total-tokens ${MAX_TOTAL_TOKENS}
llm-docsum-tgi:
image: ${REGISTRY:-opea}/llm-docsum:${TAG:-latest}
container_name: llm-docsum-gaudi-server
depends_on:
tgi-gaudi-server:
condition: service_healthy
ports:
- ${DOCSUM_PORT:-9000}:9000
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
MAX_INPUT_TOKENS: ${MAX_INPUT_TOKENS}
MAX_TOTAL_TOKENS: ${MAX_TOTAL_TOKENS}
LLM_ENDPOINT: ${LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
DocSum_COMPONENT_NAME: ${DocSum_COMPONENT_NAME}
LOGFLAG: ${LOGFLAG:-False}
restart: unless-stopped
whisper:
image: ${REGISTRY:-opea}/whisper:${TAG:-latest}
container_name: whisper-server
ports:
- "7066:7066"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HABANA_VISIBLE_DEVICES: all
OMPI_MCA_btl_vader_single_copy_mechanism: none
runtime: habana
cap_add:
- SYS_NICE
restart: unless-stopped
docsum-gaudi-backend-server:
image: ${REGISTRY:-opea}/docsum:${TAG:-latest}
container_name: docsum-gaudi-backend-server
depends_on:
- tgi-gaudi-server
- llm-docsum-tgi
ports:
- "8888:8888"
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=${LLM_SERVICE_HOST_IP}
- ASR_SERVICE_HOST_IP=${ASR_SERVICE_HOST_IP}
ipc: host
restart: always
docsum-gradio-ui:
image: ${REGISTRY:-opea}/docsum-gradio-ui:${TAG:-latest}
container_name: docsum-gaudi-ui-server
depends_on:
- docsum-gaudi-backend-server
ports:
- "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