Examples

Deployment

vLLM

Deploy Llama 3.1 with vLLM

TGI

Deploy Llama 3.1 with TGI

NIM

Deploy Llama 3.1 with NIM

Fine-tuning

Axolotl

Fine-tune Llama 3 on a custom dataset using Axolotl.

TRL

Fine-tune Llama 3.1 8B on a custom dataset using TRL.

Accelerators

AMD

Deploy and fine-tune LLMs on AMD

TPU

Deploy and fine-tune LLMs on TPU

LLMs

Llama 3.1

Deploy and fine-tune Llama 3.1

Llama 3.2

Deploy Llama 3.2 vision models

Misc

Docker Compose

Use Docker and Docker Compose inside runs