Files
Wang, Kai Lawrence 8fe19291c8 [AudioQnA] Enable vLLM and set it as default LLM serving (#1657)
Signed-off-by: Wang, Kai Lawrence <kai.lawrence.wang@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2025-03-14 09:56:33 +08:00

109 lines
3.2 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:
- ${WHISPER_SERVER_PORT:-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
speecht5-service:
image: ${REGISTRY:-opea}/speecht5-gaudi:${TAG:-latest}
container_name: speecht5-service
ports:
- ${SPEECHT5_SERVER_PORT:-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
tgi-service:
image: ghcr.io/huggingface/tgi-gaudi:2.3.1
container_name: tgi-gaudi-service
ports:
- ${LLM_SERVER_PORT:-3006}:80
volumes:
- "${MODEL_CACHE:-./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
ENABLE_HPU_GRAPH: true
LIMIT_HPU_GRAPH: true
USE_FLASH_ATTENTION: true
FLASH_ATTENTION_RECOMPUTE: true
LLM_SERVER_PORT: ${LLM_SERVER_PORT}
healthcheck:
test: ["CMD-SHELL", "curl -f http://$host_ip:${LLM_SERVER_PORT}/health || exit 1"]
interval: 10s
timeout: 10s
retries: 100
runtime: habana
cap_add:
- SYS_NICE
ipc: host
command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
audioqna-gaudi-backend-server:
image: ${REGISTRY:-opea}/audioqna:${TAG:-latest}
container_name: audioqna-gaudi-backend-server
depends_on:
- whisper-service
- tgi-service
- speecht5-service
ports:
- "3008:8888"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
- WHISPER_SERVER_HOST_IP=${WHISPER_SERVER_HOST_IP}
- WHISPER_SERVER_PORT=${WHISPER_SERVER_PORT}
- LLM_SERVER_HOST_IP=${LLM_SERVER_HOST_IP}
- LLM_SERVER_PORT=${LLM_SERVER_PORT}
- LLM_MODEL_ID=${LLM_MODEL_ID}
- SPEECHT5_SERVER_HOST_IP=${SPEECHT5_SERVER_HOST_IP}
- SPEECHT5_SERVER_PORT=${SPEECHT5_SERVER_PORT}
ipc: host
restart: always
audioqna-gaudi-ui-server:
image: ${REGISTRY:-opea}/audioqna-ui:${TAG:-latest}
container_name: audioqna-gaudi-ui-server
depends_on:
- audioqna-gaudi-backend-server
ports:
- "5173:5173"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- CHAT_URL=${BACKEND_SERVICE_ENDPOINT}
ipc: host
restart: always
networks:
default:
driver: bridge