Adding files to deploy DocSum application on ROCm vLLM (#1572)
Signed-off-by: Chingis Yundunov <YundunovCN@sibedge.com>
This commit is contained in:
committed by
GitHub
parent
1a0c5f03c6
commit
319dbdaa6b
@@ -3,15 +3,16 @@
|
||||
# Copyright (C) 2024 Advanced Micro Devices, Inc.
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
export MAX_INPUT_TOKENS=2048
|
||||
export MAX_TOTAL_TOKENS=4096
|
||||
export DOCSUM_TGI_IMAGE="ghcr.io/huggingface/text-generation-inference:2.4.1-rocm"
|
||||
export HOST_IP=''
|
||||
export DOCSUM_MAX_INPUT_TOKENS="2048"
|
||||
export DOCSUM_MAX_TOTAL_TOKENS="4096"
|
||||
export DOCSUM_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
|
||||
export HOST_IP=${host_ip}
|
||||
export DOCSUM_TGI_SERVICE_PORT="8008"
|
||||
export DOCSUM_TGI_LLM_ENDPOINT="http://${HOST_IP}:${DOCSUM_TGI_SERVICE_PORT}"
|
||||
export DOCSUM_HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
|
||||
export DOCSUM_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
|
||||
export DOCSUM_WHISPER_PORT="7066"
|
||||
export ASR_SERVICE_HOST_IP="${HOST_IP}"
|
||||
export DOCSUM_LLM_SERVER_PORT="9000"
|
||||
export DOCSUM_BACKEND_SERVER_PORT="8888"
|
||||
export DOCSUM_FRONTEND_PORT="5173"
|
||||
export DOCSUM_BACKEND_SERVER_PORT="18072"
|
||||
export DOCSUM_FRONTEND_PORT="18073"
|
||||
export BACKEND_SERVICE_ENDPOINT="http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum"
|
||||
|
||||
Reference in New Issue
Block a user