This model is intended to be used as an accelerator for granite-8b-code-instruct and takes inspiration from the Medusa speculative decoding architecture. This accelerator modifies the MLP into a multi-stage MLP, where each stage predicts a single token in the draft based on both a state vector and sampled token from the prior stage (the base model can be considered stage 0). The state vector from the base model provides contextual information to the accelerator, while conditioning on prior sampled tokens allows it to produce higher-quality draft n-grams.
Note: The underlying MLP speculator is a generic architecture that can be trained with any generative model to accelerate inference. Training is light-weight and can be completed in only a few days depending on base model size and speed.
HF_HUB_CACHE=/hf_hub_cache
chmod a+w $HF_HUB_CACHE
HF_HUB_TOKEN="your huggingface hub token"
TGIS_IMAGE=quay.io/wxpe/text-gen-server:main.ddc56ee
docker pull $TGIS_IMAGE
# optionally download granite-8b-code-instruct if the weights do not already exist
docker run --rm \
-v $HF_HUB_CACHE:/models \
-e HF_HUB_CACHE=/models \
-e TRANSFORMERS_CACHE=/models \
$TGIS_IMAGE \
text-generation-server download-weights \
ibm-granite/granite-8b-code-instruct \
--token $HF_HUB_TOKEN
# optionally download the speculator model if the weights do not already exist
docker run --rm \
-v $HF_HUB_CACHE:/models \
-e HF_HUB_CACHE=/models \
-e TRANSFORMERS_CACHE=/models \
$TGIS_IMAGE \
text-generation-server download-weights \
ibm-granite/granite-8b-code-instruct-accelerator \
--token $HF_HUB_TOKEN
# note: if the weights were downloaded separately (not with the above commands), please place them in the HF_HUB_CACHE directory and refer to them with /models/<model_name>
docker run -d --rm --gpus all \
--name my-tgis-server \
-p 8033:8033 \
-v $HF_HUB_CACHE:/models \
-e HF_HUB_CACHE=/models \
-e TRANSFORMERS_CACHE=/models \
-e MODEL_NAME=ibm-granite/granite-8b-code-instruct \
-e SPECULATOR_NAME=ibm-granite/granite-8b-code-instruct-accelerator \
-e FLASH_ATTENTION=true \
-e PAGED_ATTENTION=true \
-e DTYPE=float16 \
$TGIS_IMAGE
# check logs and wait for "gRPC server started on port 8033" and "HTTP server started on port 3000"
docker logs my-tgis-server -f
# get the client sample (Note: The first prompt will take longer as there is a warmup time)
conda create -n tgis-client-env python=3.11
conda activate tgis-client-env
git clone --branch main --single-branch https://github.com/IBM/text-generation-inference.git
cd text-generation-inference/integration_tests
make gen-client
pip install . --no-cache-dir
model=ibm-granite/granite-8b-code-instruct-accelerator
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:latest --model-id $model
