Large Language Models

Large Language Model workflows and tutorials on Saturn Cloud

This section covers Large Language Model (LLM) workflows and tutorials on Saturn Cloud.

Creating a RAG pipeline with LangChain

Create and Serve RAG Applications with Pinecone, LangChain, and MLFlow

Deploying LLMs with NVIDIA NIM

Deploy LLMs with optimal throughput and latency with NVIDIA Inference Microservices

Deploying LLMs with vLLM

Deploying LLMs with vLLM

Fine Tuning LLMs

Fine Tuning LLMs with Unsloth

Multi-Node Multi-GPU Parallel Training

Multi-Node Parallel Training with PyTorch and Tensorflow