Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
macadeliccc 
posted an update Aug 27
Post
1292
Save money on your compute bill by using LMCache to share prefix KV between 2 different vllm instances. By deploying LMCache backend along with your vLLM containers, you can share a prefix KV Cache between 2 different containers and models. It is very simple to implement into your existing stack.

Step 1: Pull docker images
docker pull apostacyh/vllm:lmcache-0.1.0

Step 2: Start vLLM + LMCache
model=mistralai/Mistral-7B-Instruct-v0.2    # Replace with your model name
sudo docker run --runtime nvidia --gpus '"device=0"' \
    -v <Huggingface cache dir on your local machine>:/root/.cache/huggingface \
    -p 8000:8000 \
    --env "HF_TOKEN=<Your huggingface access token>" \
    --ipc=host \
    --network=host \
    apostacyh/vllm:lmcache-0.1.0 \
    --model $model --gpu-memory-utilization 0.6 --port 8000 \
    --lmcache-config-file /lmcache/LMCache/examples/example-local.yaml

You can add another vLLM instance as long as its on a separate GPU by simply deploying another: 

# The second vLLM instance listens at port 8001
model=mistralai/Mistral-7B-Instruct-v0.2    # Replace with your model name
sudo docker run --runtime nvidia --gpus '"device=1"' \
    -v <Huggingface cache dir on your local machine>:/root/.cache/huggingface \
    -p 8001:8001 \
    --env "HF_TOKEN=<Your huggingface token>" \
    --ipc=host \
    --network=host \
    apostacyh/vllm:lmcache-0.1.0 \
    --model $model --gpu-memory-utilization 0.7 --port 8001 \
    --lmcache-config-file /lmcache/LMCache/examples/example.yaml

This method supports local, remote or hybrid backends so whichever vLLM deployment method you are already using should work with the LMCache container (excluding BentoML).

LMCache: https://github.com/LMCache/LMCache/tree/dev
vLLM: https://github.com/vllm-project/vllm
In this post