jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

use official docker image (#10)

Browse Source 
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
This commit is contained in:
lvliang-intel
2024-03-23 14:35:23 +08:00
committed by GitHub
parent 8b2923463a
commit c84b2cde2f
2 changed files with 12 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
ChatQnA/README.md
View File

@@ -3,7 +3,16 @@ This ChatQnA use case performs RAG using LangChain, Redis vectordb and Text Gene
# Environment Setup # Environment Setup
To use [🤗 text-generation-inference](https://github.com/huggingface/text-generation-inference) on Habana Gaudi/Gaudi2, please follow these steps: To use [🤗 text-generation-inference](https://github.com/huggingface/text-generation-inference) on Habana Gaudi/Gaudi2, please follow these steps:
## Build TGI Gaudi Docker Image ## Prepare Docker
Getting started is straightforward with the official Docker container. Simply pull the image using:
```bash
docker pull ghcr.io/huggingface/tgi-gaudi:1.2.1
```
Alternatively, you can build the Docker image yourself with:
```bash ```bash
bash ./serving/tgi_gaudi/build_docker.sh bash ./serving/tgi_gaudi/build_docker.sh
``` ```

4
ChatQnA/serving/tgi_gaudi/launch_tgi_service.sh
View File

@@ -27,9 +27,9 @@ volume=$PWD/data
# Build the Docker run command based on the number of cards # Build the Docker run command based on the number of cards
if [ "$num_cards" -eq 1 ]; then if [ "$num_cards" -eq 1 ]; then
docker_cmd="docker run -p $port_number:80 -v $volume:/data --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --ipc=host -e HTTPS_PROXY=$https_proxy -e HTTP_PROXY=$https_proxy tgi_gaudi --model-id $model_name" docker_cmd="docker run -p $port_number:80 -v $volume:/data --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --ipc=host -e HTTPS_PROXY=$https_proxy -e HTTP_PROXY=$https_proxy ghcr.io/huggingface/tgi-gaudi --model-id $model_name"
else else
docker_cmd="docker run -p $port_number:80 -v $volume:/data --runtime=habana -e PT_HPU_ENABLE_LAZY_COLLECTIVES=true -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --ipc=host -e HTTPS_PROXY=$https_proxy -e HTTP_PROXY=$https_proxy tgi_gaudi --model-id $model_name --sharded true --num-shard $num_cards" docker_cmd="docker run -p $port_number:80 -v $volume:/data --runtime=habana -e PT_HPU_ENABLE_LAZY_COLLECTIVES=true -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --ipc=host -e HTTPS_PROXY=$https_proxy -e HTTP_PROXY=$https_proxy ghcr.io/huggingface/tgi-gaudi --model-id $model_name --sharded true --num-shard $num_cards"
fi fi
# Execute the Docker run command # Execute the Docker run command