3fb60608b3
Signed-off-by: lvliang-intel <liang1.lv@intel.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
49 lines
1.3 KiB
YAML
49 lines
1.3 KiB
YAML
|
|
# Copyright (C) 2024 Intel Corporation
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
opea_micro_services:
|
|
tgi-service:
|
|
host: ${TGI_SERVICE_IP}
|
|
ports: ${TGI_SERVICE_PORT}
|
|
image: ghcr.io/huggingface/tgi-gaudi:2.0.5
|
|
volumes:
|
|
- "./data:/data"
|
|
runtime: habana
|
|
cap_add:
|
|
- SYS_NICE
|
|
ipc: host
|
|
environment:
|
|
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
|
|
HABANA_VISIBLE_DEVICES: all
|
|
OMPI_MCA_btl_vader_single_copy_mechanism: none
|
|
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
|
|
ENABLE_HPU_GRAPH: true
|
|
LIMIT_HPU_GRAPH: true
|
|
USE_FLASH_ATTENTION: true
|
|
FLASH_ATTENTION_RECOMPUTE: true
|
|
model-id: ${LLM_MODEL_ID}
|
|
llm:
|
|
host: ${LLM_SERVICE_HOST_IP}
|
|
ports: ${LLM_SERVICE_PORT}
|
|
image: opea/llm-tgi:latest
|
|
endpoint: /v1/chat/completions
|
|
environment:
|
|
TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
|
|
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
|
|
ui:
|
|
host: ${UI_SERVICE_HOST_IP}
|
|
ports:
|
|
- "5173:5173"
|
|
image: opea/codegen-ui:latest
|
|
environment:
|
|
- CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
|
|
|
|
opea_mega_service:
|
|
host: ${MEGA_SERVICE_HOST_IP}
|
|
ports: ${MEGA_SERVICE_PORT}
|
|
endpoint: /v1/codegen
|
|
image: opea/codegen:latest
|
|
mega_flow:
|
|
- llm
|