!(function () {
  var e, t, n;
  (e = "1ee05ac5e4d3b9c"),
    (t = function () {
      Reo.init({ clientID: "1ee05ac5e4d3b9c" });
    }),
    ((n = document.createElement("script")).src =
      "https://static.reo.dev/" + e + "/reo.js"),
    (n.async = !0),
    (n.onload = t),
    document.head.appendChild(n);
})();

!(function (t, e) {
  var o, n, p, r;
  e.__SV ||
    ((window.posthog = e),
    (e._i = []),
    (e.init = function (i, s, a) {
      function g(t, e) {
        var o = e.split(".");
        2 == o.length && ((t = t[o[0]]), (e = o[1])),
          (t[e] = function () {
            t.push([e].concat(Array.prototype.slice.call(arguments, 0)));
          });
      }
      ((p = t.createElement("script")).type = "text/javascript"),
        (p.async = !0),
        (p.src =
          s.api_host.replace(".i.posthog.com", "-assets.i.posthog.com") +
          "/static/array.js"),
        (r = t.getElementsByTagName("script")[0]).parentNode.insertBefore(p, r);
      var u = e;
      for (
        void 0 !== a ? (u = e[a] = []) : (a = "posthog"),
          u.people = u.people || [],
          u.toString = function (t) {
            var e = "posthog";
            return "posthog" !== a && (e += "." + a), t || (e += " (stub)"), e;
          },
          u.people.toString = function () {
            return u.toString(1) + ".people (stub)";
          },
          o =
            "init capture register register_once register_for_session unregister unregister_for_session getFeatureFlag getFeatureFlagPayload isFeatureEnabled reloadFeatureFlags updateEarlyAccessFeatureEnrollment getEarlyAccessFeatures on onFeatureFlags onSessionId getSurveys getActiveMatchingSurveys renderSurvey canRenderSurvey getNextSurveyStep identify setPersonProperties group resetGroups setPersonPropertiesForFlags resetPersonPropertiesForFlags setGroupPropertiesForFlags resetGroupPropertiesForFlags reset get_distinct_id getGroups get_session_id get_session_replay_url alias set_config startSessionRecording stopSessionRecording sessionRecordingStarted captureException loadToolbar get_property getSessionProperty createPersonProfile opt_in_capturing opt_out_capturing has_opted_in_capturing has_opted_out_capturing clear_opt_in_out_capturing debug".split(
              " "
            ),
          n = 0;
        n < o.length;
        n++
      )
        g(u, o[n]);
      e._i.push([i, s, a]);
    }),
    (e.__SV = 1));
})(document, window.posthog || []);
posthog.init("phc_7EBwiSJjUT69Jk8SP8E0YOB3Jm4UJcW8mmBUPl0w4D4", {
  api_host: "https://eu.i.posthog.com",
  person_profiles: "identified_only",
});


Step-by-Step Guide

Deploy your private API instance of Llama3.1 via the VLLM inference library.

Deploy Llama via VLLM

Prime Intellect Docs

Introduction

The most cost effective GPUs deployed in less than 1min

Quickstart - Deploy a Pod

Concepts

Run Jupyter Notebooks

Deploy Custom Docker Image

Deploy a multi-node cluster on the Prime Intellect Platform.

Deploy Multi-Node Cluster

How to use Torch FSDP to train models distributed across multiple nodes.

Run Torch FSDP

Run Megatron-Deepspeed to train models distributed across multiple nodes.

Run Megatron-Deepspeed

Run Huggingface Accelerate to train models distributed across multiple nodes.

Run Hugging Face Accelerate

Run Llama 405B inference in BF16 across multiple nodes.

Llama 405B Inference in BF16

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

Run DistillKit

Guidelines for contributing compute to decentralized compute pools.

Contribution Guidelines

Plug into the cheapest compute for your applications and workflows.

API Overview

How to generate and use authentication keys with our API

API keys

How to check gpu availability and pricing

Get Availability Information

How to provision an instance using availability data

Provision Instance

How to get pods, statuses and delete instances

Managing Pods

Get Gpu Availability

Get Cluster Availability

Get Pods

Create Pod

Get Pods History

Get Pods Status

Get Pod

Delete Pod

Add Metrics

Plug into the cheapest compute for your applications and workflows

CLI Overview

Configuration

Discord

Twitter

Blog

API Reference

CLI Reference

Platform

Support

Rent and contribute compute, and have it fully managed by Prime Intellect.

Fully Managed

Contribute your own GPUs to the compute pool.

Getting Started

On-Demand Cloud

Multi-Node Clusters

Decentralized Intelligence

Deploy Llama via VLLM

Step-by-Step Guide

Getting Started

On-Demand Cloud

Multi-Node Clusters

Decentralized Intelligence

​Step-by-Step Guide

Step-by-Step Guide