Sign inSign up

beehivelab/gpullama3.java-nvidia-openjdk-opencl

By beehivelab

Updated 11 months ago

An image for running GPULlama3.java with TornadoVM NVIDIA GPUs with OpenCL.

Image
0

604

beehivelab/gpullama3.java-nvidia-openjdk-opencl repository overview

🚀 Quick Start

1. Pull the Docker Image
docker pull beehivelab/gpullama3.java-nvidia-openjdk-opencl:latest
2. Clone the Runner Scripts
git clone https://github.com/beehive-lab/docker-gpullama3.java
cd docker-gpullama3.java

3. Download a Model
wget https://huggingface.co/beehive-lab/Llama-3.2-1B-Instruct-GGUF-FP16/resolve/main/beehive-llama-3.2-1b-instruct-fp16.gguf

4. Run a Prompt
./dockerized-llama-tornado-nvidia-opencl \
  --gpu --opencl --verbose-init \
  --model beehive-llama-3.2-1b-instruct-fp16.gguf \
  --prompt "tell me a joke"

Sample Output:

Here's one:
What do you call a fake noodle?
An impasta!

Tag summary

Content type

Image

Digest

sha256:9c1d37ad7

Size

2.3 GB

Last updated

11 months ago

docker pull beehivelab/gpullama3.java-nvidia-openjdk-opencl