Prime Intellect Docs home page

Support
Platform
Platform

Getting Started

Introduction
Quickstart - Deploy a Pod
Concepts

On-Demand Cloud

Run Jupyter Notebooks
Deploy Llama via VLLM
Deploy Custom Docker Image

Multi-Node Clusters

Deploy Multi-Node Cluster
Run Torch FSDP
Run Megatron-Deepspeed
Run Hugging Face Accelerate
Llama 405B Inference in BF16
Run DistillKit

Decentralized Intelligence

Contribute Compute
Contribution Guidelines
Contribution FAQ

Multi-Node Clusters

Run DistillKit

Distill Llama 405B into smaller models via our Multi-node offering.

Coming Soon…

Llama 405B Inference in BF16 Fully Managed

x github linkedin

Powered by Mintlify

Assistant

Responses are generated using AI and may contain mistakes.