Files
GenAIExamples/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml
lvliang-intel 1ff85f6a85 Upgrade TGI Gaudi version to v2.0.6 (#1088)
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
2024-11-12 14:38:22 +08:00

76 lines
2.0 KiB
YAML

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
services:
tgi-service:
image: ghcr.io/huggingface/tgi-gaudi:2.0.6
container_name: tgi-gaudi-server
ports:
- "8008:80"
environment:
HABANA_VISIBLE_DEVICES: all
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
ENABLE_HPU_GRAPH: true
LIMIT_HPU_GRAPH: true
USE_FLASH_ATTENTION: true
FLASH_ATTENTION_RECOMPUTE: true
volumes:
- "./data:/data"
runtime: habana
cap_add:
- SYS_NICE
ipc: host
command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
llm:
image: ${REGISTRY:-opea}/llm-docsum-tgi:${TAG:-latest}
container_name: llm-docsum-gaudi-server
depends_on:
- tgi-service
ports:
- "9000:9000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
docsum-gaudi-backend-server:
image: ${REGISTRY:-opea}/docsum:${TAG:-latest}
container_name: docsum-gaudi-backend-server
depends_on:
- tgi-service
- llm
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}
ipc: host
restart: always
docsum-gaudi-ui-server:
image: ${REGISTRY:-opea}/docsum-ui:${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=${http_proxy}
- DOC_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
ipc: host
restart: always
networks:
default:
driver: bridge