To use 🤗 text-generation-inference on Habana Gaudi/Gaudi2, follow these steps:

1. Build the Docker image located in this folder with:

   docker build -t tgi_gaudi .

2. Launch a local server instance on 1 Gaudi card:

   model=meta-llama/Llama-2-7b-hf
   volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
   
   docker run -p 8080:80 -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 tgi_gaudi --model-id $model

3. Launch a local server instance on 8 Gaudi cards:

   model=meta-llama/Llama-2-70b-hf
   volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
   
   docker run -p 8080:80 -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 tgi_gaudi --model-id $model --sharded true --num-shard 8

   Set LIMIT_HPU_GRAPH=True for larger sequence/decoding lengths(e.g. 300/212).

4. You can then send a request:

   curl 127.0.0.1:8080/generate \
     -X POST \
     -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' \
     -H 'Content-Type: application/json'

   The first call will be slower as the model is compiled.

5. To run benchmark test, please refer TGI's benchmark tool.

   To run it on the same machine, you can do the following:

   • docker exec -it <docker name> bash , pick the docker started from step 3 or 4 using docker ps
   • text-generation-benchmark -t <model-id> , pass the model-id from docker run command
   • after the completion of tests, hit ctrl+c to see the performance data summary.

For gated models such as StarCoder, you will have to pass -e HUGGING_FACE_HUB_TOKEN=<token> to the docker run command above with a valid Hugging Face Hub read token.

For more information and documentation about Text Generation Inference, checkout the README of the original repo.

Not all features of TGI are currently supported as this is still a work in progress.

New changes are added for the current release:

• Sharded feature with support for DeepSpeed-inference auto tensor parallelism. Also, use HPU graphs for performance improvement.
• Torch profile.
• Batch size bucketing for decode and prefill.

Environment Variables Added:

Maximum batch size is controlled by two arguments:

• For prefill operation, please set --max-prefill-total-tokens as bs * max-input-length, where bs is your expected maximum prefill batch size.
• For decode operation, please set --max-batch-total-tokens as bs * max-total-tokens, where bs is your expected maximum decode batch size.
• Please note that batch size will be always padded to the nearest multiplication of BATCH_BUCKET_SIZE and PREFILL_BATCH_BUCKET_SIZE.

The license to use TGI on Habana Gaudi is the one of TGI: https://github.com/huggingface/text-generation-inference/blob/main/LICENSE

Please reach out to [email protected] if you have any question.