top | item 40131316

(no title)

1 points| juliensalinas | 1 year ago

discuss

order

juliensalinas|1 year ago

Many are trying to install and deploy their own LLaMA 3 model, so here is a tutorial I just made showing how to deploy LLaMA 3 on an AWS EC2 instance: https://nlpcloud.com/how-to-install-and-deploy-llama-3-into-...

Deploying LLaMA 3 8B is fairly easy but LLaMA 3 70B is another beast. Given the amount of VRAM needed you might want to provision more than one GPU and use a dedicated inference server like vLLM in order to split your model on several GPUs.

LLaMA 3 8B requires around 16GB of disk space and 20GB of VRAM (GPU memory) in FP16. As for LLaMA 3 70B, it requires around 140GB of disk space and 160GB of VRAM in FP16.

I hope it is useful, and if you have questions please don't hesitate to ask!

Julien