Files
GenAIExamples/AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml
XinyaoWa d73129cbf0 Refactor folder to support different vendors (#743)
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>
Signed-off-by: chensuyue <suyue.chen@intel.com>
2024-09-10 23:27:19 +08:00

115 lines
3.1 KiB
YAML

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
services:
whisper-service:
image: ${REGISTRY:-opea}/whisper-gaudi:${TAG:-latest}
container_name: whisper-service
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
asr:
image: ${REGISTRY:-opea}/asr:${TAG:-latest}
container_name: asr-service
ports:
- "3001:9099"
ipc: host
environment:
ASR_ENDPOINT: ${ASR_ENDPOINT}
speecht5-service:
image: ${REGISTRY:-opea}/speecht5-gaudi:${TAG:-latest}
container_name: speecht5-service
ports:
- "7055:7055"
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
tts:
image: ${REGISTRY:-opea}/tts:${TAG:-latest}
container_name: tts-service
ports:
- "3002:9088"
ipc: host
environment:
TTS_ENDPOINT: ${TTS_ENDPOINT}
tgi-service:
image: ghcr.io/huggingface/tgi-gaudi:2.0.1
container_name: tgi-gaudi-server
ports:
- "3006:80"
volumes:
- "./data:/data"
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_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
runtime: habana
cap_add:
- SYS_NICE
ipc: host
command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
llm:
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
container_name: llm-tgi-gaudi-server
depends_on:
- tgi-service
ports:
- "3007:9000"
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
audioqna-gaudi-backend-server:
image: ${REGISTRY:-opea}/audioqna:${TAG:-latest}
container_name: audioqna-gaudi-backend-server
depends_on:
- asr
- llm
- tts
ports:
- "3008:8888"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
- ASR_SERVICE_HOST_IP=${ASR_SERVICE_HOST_IP}
- ASR_SERVICE_PORT=${ASR_SERVICE_PORT}
- LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
- LLM_SERVICE_PORT=${LLM_SERVICE_PORT}
- TTS_SERVICE_HOST_IP=${TTS_SERVICE_HOST_IP}
- TTS_SERVICE_PORT=${TTS_SERVICE_PORT}
ipc: host
restart: always
networks:
default:
driver: bridge