9180f1066d
Set vllm as default llm serving, and add related docker compose files, readmes, and test scripts. Issue: https://github.com/opea-project/GenAIExamples/issues/1436 Signed-off-by: letonghan <letong.han@intel.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
100 lines
3.0 KiB
YAML
100 lines
3.0 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: codetrans-gaudi-tgi-service
|
|
ports:
|
|
- "8008:80"
|
|
volumes:
|
|
- "${MODEL_CACHE}:/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
|
|
runtime: habana
|
|
cap_add:
|
|
- SYS_NICE
|
|
ipc: host
|
|
command: --model-id ${LLM_MODEL_ID} --max-input-length 2048 --max-total-tokens 4096
|
|
llm:
|
|
image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest}
|
|
container_name: codetrans-gaudi-llm-server
|
|
depends_on:
|
|
- tgi-service
|
|
ports:
|
|
- "9000:9000"
|
|
ipc: host
|
|
environment:
|
|
no_proxy: ${no_proxy}
|
|
http_proxy: ${http_proxy}
|
|
https_proxy: ${https_proxy}
|
|
LLM_ENDPOINT: ${LLM_ENDPOINT}
|
|
LLM_MODEL_ID: ${LLM_MODEL_ID}
|
|
LLM_COMPONENT_NAME: ${LLM_COMPONENT_NAME}
|
|
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
|
|
restart: unless-stopped
|
|
codetrans-gaudi-backend-server:
|
|
image: ${REGISTRY:-opea}/codetrans:${TAG:-latest}
|
|
container_name: codetrans-gaudi-backend-server
|
|
depends_on:
|
|
- tgi-service
|
|
- llm
|
|
ports:
|
|
- "${BACKEND_SERVICE_PORT:-7777}:7777"
|
|
environment:
|
|
- no_proxy=${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
|
|
codetrans-gaudi-ui-server:
|
|
image: ${REGISTRY:-opea}/codetrans-ui:${TAG:-latest}
|
|
container_name: codetrans-gaudi-ui-server
|
|
depends_on:
|
|
- codetrans-gaudi-backend-server
|
|
ports:
|
|
- "${FRONTEND_SERVICE_PORT:-5173}:5173"
|
|
environment:
|
|
- no_proxy=${no_proxy}
|
|
- https_proxy=${https_proxy}
|
|
- http_proxy=${http_proxy}
|
|
- BASE_URL=${BACKEND_SERVICE_ENDPOINT}
|
|
ipc: host
|
|
restart: always
|
|
codetrans-gaudi-nginx-server:
|
|
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
|
|
container_name: codetrans-gaudi-nginx-server
|
|
depends_on:
|
|
- codetrans-gaudi-backend-server
|
|
- codetrans-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
|