Pulumi Blog: Llama

Run Open-Source LLMs on AWS EC2 with Ollama and Pulumi

Engin Diri — Mon, 27 Jan 2025 00:00:00 +0000

TL;DR. Want to self-host an open-source LLM on AWS? Use a g4dn.xlarge ($0.526/hr on-demand, 16 GB GPU memory) for 7B/8B models, a g5.xlarge ($1.006/hr, 24 GB) for 13B–14B models, a g5.2xlarge ($1.212/hr, 24 GB) for 32B models, or a g6e.2xlarge ($2.242/hr, 48 GB) for 70B models. Deploy with the Pulumi program below and Ollama will run any model from its library: DeepSeek-R1, Llama 3, Qwen, or Mistral, with a one-line change.

This guide walks through that deployment end-to-end: a single Pulumi program that provisions a GPU-enabled EC2 instance, installs Ollama and Open WebUI via cloud-init, and exposes both a chat UI and an OpenAI-compatible API. The model is configurable, so you can swap DeepSeek-R1 for Llama 3.1, Qwen 2.5, or Mistral without touching the infrastructure code.

Why run open-source LLMs on AWS EC2?

Self-hosting an open-source LLM on AWS gives you three things hosted APIs can’t: data stays inside your VPC, per-token costs collapse to a flat hourly rate at high volume, and you can fine-tune or quantize models freely under permissive licenses. Ollama handles all three concerns from a single binary: it downloads, manages, and serves models behind an OpenAI-compatible API on port 11434.

The original version of this post focused on DeepSeek-R1 because it landed in late January 2025 and reset expectations for what an open-weight reasoning model could do. DeepSeek-R1 is still an excellent default (MIT-licensed, strong on math and coding, with distilled 1.5B–70B variants) but the same infrastructure runs Meta’s Llama 3, Alibaba’s Qwen, and Mistral equally well. Picking a model is now a config change, not an infrastructure decision.

For reference, DeepSeek-R1 scores 79.8% on AIME 2024 (vs. 79.2% for OpenAI o1-1217), 97.3% on MATH-500 (vs. 96.4%), 96.3% on Codeforces (vs. 96.6%), and 49.2% on SWE-bench Verified (vs. 48.9%)—near-parity with closed frontier models on most reasoning benchmarks, with the same caveat that benchmark scores age fast.

You might also like:

Which models can I run, and which EC2 instance do I need?

The bottleneck for inference is GPU memory (VRAM): the model weights have to fit in it, plus a few GB of headroom for the KV cache. The table below maps the most common Ollama models to the smallest AWS GPU instance that comfortably runs them at 4-bit (Q4) quantization, which is what ollama pull <model> gives you by default.

Model family	Sizes	Approx. VRAM (Q4)	Smallest EC2 instance	On-demand price (us-east-1)
DeepSeek-R1 (distill)	1.5B / 7B / 8B	1–6 GB	`g4dn.xlarge` (T4, 16 GB)	$0.526/hr
Llama 3.1 / Llama 3.2	8B	~5 GB	`g4dn.xlarge` (T4, 16 GB)	$0.526/hr
Qwen 2.5	7B	~5 GB	`g4dn.xlarge` (T4, 16 GB)	$0.526/hr
Mistral 7B / Mistral Nemo	7B / 12B	5–8 GB	`g4dn.xlarge` (T4, 16 GB)	$0.526/hr
DeepSeek-R1 (distill)	14B	~10 GB	`g5.xlarge` (A10G, 24 GB)	$1.006/hr
Llama 3.3 / DeepSeek-R1	32B / 32B distill	~20 GB	`g5.2xlarge` (A10G, 24 GB)	$1.212/hr
Llama 3.1 / DeepSeek-R1	70B	~42 GB	`g6e.2xlarge` (L40S, 48 GB)	$2.242/hr
DeepSeek-R1 (full)	671B (MoE)	400 GB+	`p5.48xlarge` or multi-node	$98.32/hr

For most workloads—internal tools, RAG backends, code assistants—a g4dn.xlarge running an 8B model is the right starting point. Move up only if quality is the bottleneck.

How much does this cost vs. hosted APIs?

A g4dn.xlarge running 24/7 costs ~$378/month on-demand, or ~$237/month with a 1-year reserved instance. Whether that’s cheaper than a hosted API depends entirely on your token volume.

Compare against hosted pricing as of April 2026 (input + output blended, rough numbers):

Provider	Model	Approx. blended price
OpenAI	GPT-4o-mini	~$0.30 per 1M tokens
OpenAI	GPT-4o	~$5.00 per 1M tokens
Anthropic	Claude Sonnet 4	~$6.00 per 1M tokens
DeepSeek (hosted)	DeepSeek-V3	~$0.50 per 1M tokens

A g4dn.xlarge running Llama 3.1 8B sustains roughly 40–60 tokens/sec under single-user load, or about 100–155M tokens/month at 100% utilization. At that ceiling the effective rate is ~$2.40/M tokens—cheaper than GPT-4o or Claude, more expensive than GPT-4o-mini or DeepSeek’s own hosted API.

The takeaway: self-hosting wins on data residency, latency, and predictable cost at high utilization. Hosted APIs win below ~10M tokens/month or when you need frontier-class quality. Run the math against your actual token volume before committing.

How do I deploy Ollama on AWS EC2 with Pulumi?

Prerequisites

Before we start, make sure you have the following:

An AWS account
Pulumi CLI installed
AWS CLI installed and configured
A working understanding of Ollama

What is Ollama?

Ollama is an open-source runtime that downloads, manages, and serves large language models from a single binary. It runs on macOS, Linux, and Windows, supports GPU acceleration through CUDA and Metal, and exposes both a native HTTP API and an OpenAI-compatible API on port 11434. Most clients written for the OpenAI SDK work against an Ollama endpoint with only a base-URL change.

It supports the major open-weight families—DeepSeek-R1, Llama 3, Qwen, Mistral, Gemma, Phi—plus quantized and distilled variants for each. You pull a model by name and tag (ollama pull llama3.1:8b) and run it (ollama run llama3.1:8b); Ollama handles the rest.

Architecture

Create a new Pulumi project

First, scaffold a new Pulumi project. Run the following from an empty directory:

# Replace <language> with typescript, python, go, csharp, or yaml
pulumi new aws-<language>

Pick the language you are most comfortable with. The template installs the AWS provider and creates a working sample. You can delete the sample code—we’ll replace it with the snippets below.

Step 1: Create an instance role with S3 access

The EC2 instance needs to download NVIDIA drivers from a public AWS-managed S3 bucket. Create an IAM role with S3 read access and attach it to an instance profile:

import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";
import * as fs from "fs";

const role = new aws.iam.Role("deepSeekRole", {
 name: "deepseek-role",
 assumeRolePolicy: JSON.stringify({
 Version: "2012-10-17",
 Statement: [
 {
 Action: "sts:AssumeRole",
 Effect: "Allow",
 Principal: {
 Service: "ec2.amazonaws.com",
 },
 },
 ],
 }),
});

new aws.iam.RolePolicyAttachment("deepSeekS3Policy", {
 policyArn: "arn:aws:iam::aws:policy/AmazonS3ReadOnlyAccess",
 role: role.name,
});

const instanceProfile = new aws.iam.InstanceProfile("deepSeekProfile", {
 name: "deepseek-profile",
 role: role.name,
});

import pulumi
import pulumi_aws as aws
import json
import os

# IAM Role for EC2 instances
role = aws.iam.Role(
 "deepSeekRole",
 name="deepseek-role",
 assume_role_policy=json.dumps(
 {
 "Version": "2012-10-17",
 "Statement": [
 {
 "Action": "sts:AssumeRole",
 "Effect": "Allow",
 "Principal": {
 "Service": "ec2.amazonaws.com",
 },
 }
 ],
 }
 ),
)

# Attach S3 read-only policy to the IAM Role
iam_policy_attachment = aws.iam.RolePolicyAttachment(
 "deepSeekS3Policy",
 policy_arn="arn:aws:iam::aws:policy/AmazonS3ReadOnlyAccess",
 role=role.name,
)

# Instance Profile containing the IAM Role
instance_profile = aws.iam.InstanceProfile(
 "deepSeekProfile", name="deepseek-profile", role=role.name
)

package main

import (
 "encoding/json"
 "os"

 "github.com/pulumi/pulumi-aws/sdk/v6/go/aws/ec2"
 "github.com/pulumi/pulumi-aws/sdk/v6/go/aws/iam"
 "github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
 pulumi.Run(func(ctx *pulumi.Context) error {
 rolePolicy, err := json.Marshal(map[string]interface{}{
 "Version": "2012-10-17",
 "Statement": []map[string]interface{}{
 {
 "Action": "sts:AssumeRole",
 "Effect": "Allow",
 "Principal": map[string]interface{}{"Service": "ec2.amazonaws.com"},
 },
 },
 })
 if err != nil {
 return err
 }

 role, err := iam.NewRole(ctx, "deepSeekRole", &iam.RoleArgs{
 Name: pulumi.String("deepseek-role"),
 AssumeRolePolicy: pulumi.String(rolePolicy),
 })
 if err != nil {
 return err
 }

 // Attach S3 read-only policy to the IAM Role
 _, err = iam.NewRolePolicyAttachment(ctx, "deepSeekS3Policy", &iam.RolePolicyAttachmentArgs{
 PolicyArn: pulumi.String("arn:aws:iam::aws:policy/AmazonS3ReadOnlyAccess"),
 Role: role.Name,
 })
 if err != nil {
 return err
 }

 // Instance Profile containing the IAM Role
 instanceProfile, err := iam.NewInstanceProfile(ctx, "deepSeekProfile", &iam.InstanceProfileArgs{
 Name: pulumi.String("deepseek-profile"),
 Role: role.Name,
 })
 if err != nil {
 return err
 }
 return nil
 })
}

using Pulumi;
using Pulumi.Aws.Ec2;
using Pulumi.Aws.Iam;
using System.Collections.Generic;
using System.IO;
using Pulumi.Aws.Ec2.Inputs;
using System.Text.Json;

return await Deployment.RunAsync(() =>
{
 var rolePolicy = JsonSerializer.Serialize(new Dictionary<string, object>
 {
 {
 ["Version"] = "2012-10-17",
 ["Statement"] = new[]
 {
 new Dictionary<string, object>
 {
 ["Action"] = "sts:AssumeRole",
 ["Effect"] = "Allow",
 ["Principal"] = new Dictionary<string, string>
 {
 ["Service"] = "ec2.amazonaws.com"
 }
 }
 }
 });

 var role = new Role("deepSeekRole", new RoleArgs
 {
 Name = "deepseek-role",
 AssumeRolePolicy = rolePolicy
 });

 var rolePolicyAttachment = new RolePolicyAttachment("deepSeekS3Policy", new RolePolicyAttachmentArgs
 {
 PolicyArn = "arn:aws:iam::aws:policy/AmazonS3ReadOnlyAccess",
 Role = role.Name
 });

 var instanceProfile = new InstanceProfile("deepSeekProfile", new InstanceProfileArgs
 {
 Name = "deepseek-profile",
 Role = role.Name
 });

 var vpc = new Vpc("deepSeekVpc", new VpcArgs
 {
 CidrBlock = "10.0.0.0/16",
 EnableDnsHostnames = true,
 EnableDnsSupport = true
 });

 var subnet = new Subnet("deepSeekSubnet", new SubnetArgs
 {
 VpcId = vpc.Id,
 CidrBlock = "10.0.48.0/20",
 AvailabilityZone = "eu-central-1a",
 MapPublicIpOnLaunch = true
 });

 var internetGateway = new InternetGateway("deepSeekInternetGateway", new InternetGatewayArgs
 {
 VpcId = vpc.Id
 });

 var routeTable = new RouteTable("deepSeekRouteTable", new RouteTableArgs

name: deepseek-ollama-yaml
description: DeepSeek Ollama AWS example
runtime: yaml

variables:
 publicKey:
 fn::readFile: ./deepseek.rsa
 userData:
 fn::readFile: ./cloud-init.yaml
 amiFilter: "amzn2-ami-hvm-*-x86_64-gp2"
 amiOwner: "137112412989"
 amiId:
 fn::invoke:
 function: aws:ec2:getAmi
 arguments:
 filters:
 - name: name
 values: ["${amiFilter}"]
 owners: ["${amiOwner}"]
 mostRecent: true
 return: id

resources:
 deepSeekRole:
 type: aws:iam:Role
 properties:
 name: deepseek-role
 assumeRolePolicy: |
 {
 "Version": "2012-10-17",
 "Statement": [
 {
 "Action": "sts:AssumeRole",
 "Effect": "Allow",
 "Principal": {
 "Service": "ec2.amazonaws.com"
 }
 }
 ]
 }

 deepSeekS3Policy:
 type: aws:iam:RolePolicyAttachment
 properties:
 role: ${deepSeekRole.name}
 policyArn: arn:aws:iam::aws:policy/AmazonS3ReadOnlyAccess

 deepSeekProfile:
 type: aws:iam:InstanceProfile
 properties:
 name: deepseek-profile
 role: ${deepSeekRole.name}

Step 2: Create the network

Next, create the VPC, subnet, internet gateway, and route table. The security group opens ports 22 (SSH), 3000 (Open WebUI), and 11434 (Ollama API):

const vpc = new aws.ec2.Vpc("deepSeekVpc", {
 cidrBlock: "10.0.0.0/16",
 enableDnsHostnames: true,
 enableDnsSupport: true,
});

const subnet = new aws.ec2.Subnet("deepSeekSubnet", {
 vpcId: vpc.id,
 cidrBlock: "10.0.48.0/20",
 availabilityZone: pulumi.interpolate`${aws.getAvailabilityZones().then(it => it.names[0])}`,
 mapPublicIpOnLaunch: true,
});

const internetGateway = new aws.ec2.InternetGateway("deepSeekInternetGateway", {
 vpcId: vpc.id,
});

const routeTable = new aws.ec2.RouteTable("deepSeekRouteTable", {
 vpcId: vpc.id,
 routes: [
 {
 cidrBlock: "0.0.0.0/0",
 gatewayId: internetGateway.id,
 },
 ],
});

const routeTableAssociation = new aws.ec2.RouteTableAssociation("deepSeekRouteTableAssociation", {
 subnetId: subnet.id,
 routeTableId: routeTable.id,
});

const securityGroup = new aws.ec2.SecurityGroup("deepSeekSecurityGroup", {
 vpcId: vpc.id,
 egress: [
 {
 fromPort: 0,
 toPort: 0,
 protocol: "-1",
 cidrBlocks: ["0.0.0.0/0"],
 },
 ],
 ingress: [
 {
 fromPort: 22,
 toPort: 22,
 protocol: "tcp",
 cidrBlocks: ["0.0.0.0/0"],
 },
 {
 fromPort: 3000,
 toPort: 3000,
 protocol: "tcp",
 cidrBlocks: ["0.0.0.0/0"],
 },
 {
 fromPort: 11434,
 toPort: 11434,
 protocol: "tcp",
 cidrBlocks: ["0.0.0.0/0"],
 },
 ],
});


# Create a VPC
vpc = aws.ec2.Vpc(
 "deepSeekVpc",
 cidr_block="10.0.0.0/16",
 enable_dns_hostnames=True,
 enable_dns_support=True,
)

# Create a subnet
subnet = aws.ec2.Subnet(
 "deepSeekSubnet",
 vpc_id=vpc.id,
 cidr_block="10.0.48.0/20",
 availability_zone="eu-central-1a",
 map_public_ip_on_launch=True,
)

# Create an internet gateway
internet_gateway = aws.ec2.InternetGateway("deepSeekInternetGateway", vpc_id=vpc.id)

# Create a route table and route table association
route_table = aws.ec2.RouteTable(
 "deepSeekRouteTable",
 vpc_id=vpc.id,
 routes=[
 aws.ec2.RouteTableRouteArgs(
 cidr_block="0.0.0.0/0", gateway_id=internet_gateway.id
 )
 ],
)

route_table_association = aws.ec2.RouteTableAssociation(
 "deepSeekRouteTableAssociation", subnet_id=subnet.id, route_table_id=route_table.id
)

# Create a security group
security_group = aws.ec2.SecurityGroup(
 "deepSeekSecurityGroup",
 vpc_id=vpc.id,
 egress=[
 {
 "from_port": 0,
 "to_port": 0,
 "protocol": "-1",
 "cidr_blocks": ["0.0.0.0/0"],
 }
 ],
 ingress=[
 {
 "from_port": 22,
 "to_port": 22,
 "protocol": "tcp",
 "cidr_blocks": ["0.0.0.0/0"],
 },
 {
 "from_port": 3000,
 "to_port": 3000,
 "protocol": "tcp",
 "cidr_blocks": ["0.0.0.0/0"],
 },
 {
 "from_port": 11434,
 "to_port": 11434,
 "protocol": "tcp",
 "cidr_blocks": ["0.0.0.0/0"],
 },
 ],
)

package main

import (
 "encoding/json"
 "os"

 "github.com/pulumi/pulumi-aws/sdk/v6/go/aws/ec2"
 "github.com/pulumi/pulumi-aws/sdk/v6/go/aws/iam"
 "github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
 pulumi.Run(func(ctx *pulumi.Context) error {
 // omitted for brevity
 }

 // Create a VPC
 vpc, err := ec2.NewVpc(ctx, "deepSeekVpc", &ec2.VpcArgs{
 CidrBlock: pulumi.String("10.0.0.0/16"),
 EnableDnsHostnames: pulumi.Bool(true),
 EnableDnsSupport: pulumi.Bool(true),
 })
 if err != nil {
 return err
 }

 // Create a subnet
 subnet, err := ec2.NewSubnet(ctx, "deepSeekSubnet", &ec2.SubnetArgs{
 VpcId: vpc.ID(),
 CidrBlock: pulumi.String("10.0.48.0/20"),
 AvailabilityZone: pulumi.String("eu-central-1a"),
 MapPublicIpOnLaunch: pulumi.Bool(true),
 })
 if err != nil {
 return err
 }

 // Create an internet gateway
 internetGateway, err := ec2.NewInternetGateway(ctx, "deepSeekInternetGateway", &ec2.InternetGatewayArgs{
 VpcId: vpc.ID(),
 })
 if err != nil {
 return err
 }

 // Create a route table and route table association
 routeTable, err := ec2.NewRouteTable(ctx, "deepSeekRouteTable", &ec2.RouteTableArgs{
 VpcId: vpc.ID(),
 Routes: ec2.RouteTableRouteArray{
 &ec2.RouteTableRouteArgs{
 CidrBlock: pulumi.String("0.0.0.0/0"),
 GatewayId: internetGateway.ID(),
 },
 },
 })
 if err != nil {
 return err
 }

 _, err = ec2.NewRouteTableAssociation(ctx, "deepSeekRouteTableAssociation", &ec2.RouteTableAssociationArgs{
 SubnetId: subnet.ID(),
 RouteTableId: routeTable.ID(),
 })
 if err != nil {
 return err
 }

 // Create a security group
 securityGroup, err := ec2.NewSecurityGroup(ctx, "deepSeekSecurityGroup", &ec2.SecurityGroupArgs{
 VpcId: vpc.ID(),
 Egress: ec2.SecurityGroupEgressArray{
 &ec2.SecurityGroupEgressArgs{
 FromPort: pulumi.Int(0),
 ToPort: pulumi.Int(0),
 Protocol: pulumi.String("-1"),
 CidrBlocks: pulumi.StringArray{pulumi.String("0.0.0.0/0")},
 },
 },
 Ingress: ec2.SecurityGroupIngressArray{
 &ec2.SecurityGroupIngressArgs{
 FromPort: pulumi.Int(22),
 ToPort: pulumi.Int(22),
 Protocol: pulumi.String("tcp"),
 CidrBlocks: pulumi.StringArray{pulumi.String("0.0.0.0/0")},
 },
 &ec2.SecurityGroupIngressArgs{
 FromPort: pulumi.Int(3000),
 ToPort: pulumi.Int(3000),
 Protocol: pulumi.String("tcp"),
 CidrBlocks: pulumi.StringArray{pulumi.String("0.0.0.0/0")},
 },
 &ec2.SecurityGroupIngressArgs{
 FromPort: pulumi.Int(11434),
 ToPort: pulumi.Int(11434),
 Protocol: pulumi.String("tcp"),
 CidrBlocks: pulumi.StringArray{pulumi.String("0.0.0.0/0")},
 },
 },
 })
 if err != nil {
 return err
 }

 return nil
 })
}

using Pulumi;
using Pulumi.Aws.Ec2;
using Pulumi.Aws.Iam;
using System.Collections.Generic;
using System.IO;
using Pulumi.Aws.Ec2.Inputs;
using System.Text.Json;

return await Deployment.RunAsync(() =>
{
 var rolePolicy = JsonSerializer.Serialize(new Dictionary<string, object>
 {
 // omitted for brevity
 {
 VpcId = vpc.Id,
 Routes =
 {
 new RouteTableRouteArgs
 {
 CidrBlock = "0.0.0.0/0",
 GatewayId = internetGateway.Id
 }
 }
 });

 var routeTableAssociation = new RouteTableAssociation("deepSeekRouteTableAssociation", new RouteTableAssociationArgs
 {
 SubnetId = subnet.Id,
 RouteTableId = routeTable.Id
 });

 var securityGroup = new SecurityGroup("deepSeekSecurityGroup", new SecurityGroupArgs
 {
 VpcId = vpc.Id,
 Egress =
 {
 new SecurityGroupEgressArgs
 {
 FromPort = 0,
 ToPort = 0,
 Protocol = "-1",
 CidrBlocks = { "0.0.0.0/0" }
 }
 },
 Ingress =
 {
 new SecurityGroupIngressArgs
 {
 FromPort = 22,
 ToPort = 22,
 Protocol = "tcp",
 CidrBlocks = { "0.0.0.0/0" }
 },
 new SecurityGroupIngressArgs
 {
 FromPort = 3000,
 ToPort = 3000,
 Protocol = "tcp",
 CidrBlocks = { "0.0.0.0/0" }
 },
 new SecurityGroupIngressArgs
 {
 FromPort = 11434,
 ToPort = 11434,
 Protocol = "tcp",
 CidrBlocks = { "0.0.0.0/0" }
 }
 }
 });

 var publicKey = File.ReadAllText("deepseek.rsa");
 var keyPair = new KeyPair("deepSeekKey", new KeyPairArgs
 {
 PublicKey = publicKey
 });

 var amazonLinux = Pulumi.Aws.Ec2.GetAmi.Invoke(new()
 {
 MostRecent = true,
 Filters = new[]
 {
 new GetAmiFilterInputArgs
 {
 Name = "name",
 Values = new[] { "amzn2-ami-hvm-*-x86_64-gp2" }
 },
 new GetAmiFilterInputArgs
 {
 Name = "architecture",


 deepSeekVpc:
 type: aws:ec2:Vpc
 properties:
 cidrBlock: 10.0.0.0/16
 enableDnsHostnames: true
 enableDnsSupport: true

 deepSeekSubnet:
 type: aws:ec2:Subnet
 properties:
 vpcId: ${deepSeekVpc.id}
 cidrBlock: 10.0.48.0/20
 availabilityZone: eu-central-1a
 mapPublicIpOnLaunch: true

 deepSeekInternetGateway:
 type: aws:ec2:InternetGateway
 properties:
 vpcId: ${deepSeekVpc.id}

 deepSeekRouteTable:
 type: aws:ec2:RouteTable
 properties:
 vpcId: ${deepSeekVpc.id}
 routes:
 - cidrBlock: 0.0.0.0/0
 gatewayId: ${deepSeekInternetGateway.id}

 deepSeekRouteTableAssociation:
 type: aws:ec2:RouteTableAssociation
 properties:
 subnetId: ${deepSeekSubnet.id}
 routeTableId: ${deepSeekRouteTable.id}

 deepSeekSecurityGroup:
 type: aws:ec2:SecurityGroup
 properties:
 vpcId: ${deepSeekVpc.id}
 ingress:
 - fromPort: 22
 toPort: 22
 protocol: tcp
 cidrBlocks:
 - 0.0.0.0/0
 - fromPort: 3000
 toPort: 3000
 protocol: tcp
 cidrBlocks:
 - 0.0.0.0/0
 - fromPort: 11434
 toPort: 11434
 protocol: tcp
 cidrBlocks:
 - 0.0.0.0/0
 egress:
 - fromPort: 0
 toPort: 0
 protocol: -1
 cidrBlocks:
 - 0.0.0.0/0

Step 3: Launch the GPU EC2 instance

Now create the EC2 instance itself. The example uses Amazon Linux because the NVIDIA driver install path is well-trodden, plus an SSH key pair you generate locally.

The default instance type is g4dn.xlarge—the cheapest option that fits any 7B/8B model. Bump it up if you picked a larger model from the table above: g5.xlarge for 13B–14B, g5.2xlarge for 32B, g6e.2xlarge for 70B. AWS publishes full specs for the G4, G5, and G6 families.

Generate the key pair if you don’t already have one:

openssl genrsa -out deepseek.pem 2048
openssl rsa -in deepseek.pem -pubout > deepseek.pub
ssh-keygen -f mykey.pub -i -mPKCS8 > deepseek.pem

const keyPair = new aws.ec2.KeyPair("deepSeekKey", {
 publicKey: pulumi.output(fs.readFileSync("deepseek.rsa", "utf-8")),
});

const deepSeekAmi = aws.ec2
 .getAmi({
 filters: [
 {
 name: "name",
 values: ["amzn2-ami-hvm-2.0.*-x86_64-gp2"],
 },
 {
 name: "architecture",
 values: ["x86_64"],
 },
 ],
 owners: ["137112412989"], // Amazon
 mostRecent: true,
 })
 .then(ami => ami.id);

const deepSeekInstance = new aws.ec2.Instance("deepSeekInstance", {
 ami: deepSeekAmi,
 instanceType: "g4dn.xlarge",
 keyName: keyPair.keyName,
 rootBlockDevice: {
 volumeSize: 100,
 volumeType: "gp3",
 },
 subnetId: subnet.id,
 vpcSecurityGroupIds: [securityGroup.id],
 iamInstanceProfile: instanceProfile.name,
 userData: fs.readFileSync("cloud-init.yaml", "utf-8"),
 tags: {
 Name: "deepSeek-server",
 },
});

export const amiId = deepSeekAmi;
export const instanceId = deepSeekInstance.id;
export const instancePublicDns = deepSeekInstance.publicIp;


# Key pair for SSH access
public_key = open("deepseek.rsa", "r").read()
key_pair = aws.ec2.KeyPair("deepSeekKey", public_key=public_key)


# Get the latest Amazon Linux 2 AMI
ami = aws.ec2.get_ami(
 filters=[
 {"name": "name", "values": ["amzn2-ami-hvm-2.0.*-x86_64-gp2"]},
 {"name": "architecture", "values": ["x86_64"]},
 ],
 owners=["137112412989"], # Amazon
 most_recent=True,
).id

# Create an EC2 instance
user_data = open("cloud-init.yaml", "r").read()
instance = aws.ec2.Instance(
 "deepSeekInstance",
 ami=ami,
 instance_type="g4dn.xlarge",
 key_name=key_pair.key_name,
 root_block_device=aws.ec2.InstanceRootBlockDeviceArgs(
 volume_size=100, volume_type="gp3"
 ),
 subnet_id=subnet.id,
 vpc_security_group_ids=[security_group.id],
 iam_instance_profile=instance_profile.name,
 user_data=user_data,
 tags={"Name": "deepSeek-server"},
)

pulumi.export("amiId", ami)
pulumi.export("instanceId", instance.id)
pulumi.export("instancePublicDns", instance.public_ip)

package main

import (
 "encoding/json"
 "os"

 "github.com/pulumi/pulumi-aws/sdk/v6/go/aws/ec2"
 "github.com/pulumi/pulumi-aws/sdk/v6/go/aws/iam"
 "github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
 pulumi.Run(func(ctx *pulumi.Context) error {
 // omitted for brevity

 // Key pair for SSH access
 publicKey, err := os.ReadFile("deepseek.rsa")
 if err != nil {
 return err
 }

 keyPair, err := ec2.NewKeyPair(ctx, "deepSeekKey", &ec2.KeyPairArgs{
 PublicKey: pulumi.String(string(publicKey)),
 })
 if err != nil {
 return err
 }

 // Get the latest Amazon Linux 2 AMI
 mostRecent := true
 ami, err := ec2.LookupAmi(ctx, &ec2.LookupAmiArgs{
 Filters: []ec2.GetAmiFilter{
 {
 Name: "name",
 Values: []string{"amzn2-ami-hvm-2.0.*-x86_64-gp2"},
 },
 {
 Name: "architecture",
 Values: []string{"x86_64"},
 },
 },
 Owners: []string{"137112412989"},
 MostRecent: &mostRecent,
 })
 if err != nil {
 return err
 }

 // Create an EC2 instance
 userData, err := os.ReadFile("cloud-init.yaml")
 if err != nil {
 return err
 }

 instance, err := ec2.NewInstance(ctx, "deepSeekInstance", &ec2.InstanceArgs{
 Ami: pulumi.String(ami.Id),
 InstanceType: pulumi.String("g4dn.xlarge"),
 KeyName: keyPair.KeyName,
 RootBlockDevice: &ec2.InstanceRootBlockDeviceArgs{
 VolumeSize: pulumi.Int(100),
 VolumeType: pulumi.String("gp3"),
 },
 SubnetId: subnet.ID(),
 VpcSecurityGroupIds: pulumi.StringArray{securityGroup.ID()},
 IamInstanceProfile: instanceProfile.Name,
 UserData: pulumi.String(string(userData)),
 Tags: pulumi.StringMap{
 "Name": pulumi.String("deepSeek-server"),
 },
 })
 if err != nil {
 return err
 }

 ctx.Export("amiId", pulumi.String(ami.Id))
 ctx.Export("instanceId", instance.ID())
 ctx.Export("instancePublicDns", instance.PublicIp)

 return nil
 })
}

using Pulumi;
using Pulumi.Aws.Ec2;
using Pulumi.Aws.Iam;
using System.Collections.Generic;
using System.IO;
using Pulumi.Aws.Ec2.Inputs;
using System.Text.Json;

return await Deployment.RunAsync(() =>
{
 var rolePolicy = JsonSerializer.Serialize(new Dictionary<string, object>
 {
 // omitted for brevity
 Name = "architecture",
 Values = new[] { "x86_64" }
 }
 },
 Owners = new[] { "137112412989" }
 });

 var userData = File.ReadAllText("cloud-init.yaml");
 var instance = new Instance("deepSeekInstance", new InstanceArgs
 {
 Ami = amazonLinux.Apply(r => r.Id),
 InstanceType = "g4dn.xlarge",
 KeyName = keyPair.KeyName,
 RootBlockDevice = new InstanceRootBlockDeviceArgs
 {
 VolumeSize = 100,
 VolumeType = "gp3"
 },
 SubnetId = subnet.Id,
 VpcSecurityGroupIds = { securityGroup.Id },
 IamInstanceProfile = instanceProfile.Name,
 UserData = userData,
 Tags = { { "Name", "deepSeek-server" } }
 });

 return new Dictionary<string, object?>
 {
 ["amiId"] = amazonLinux.Apply(r => r.Id),
 ["instanceId"] = instance.Id,
 ["instancePublicDns"] = instance.PublicIp
 };
});


 deepSeekKey:
 type: aws:ec2:KeyPair
 properties:
 publicKey: ${publicKey}

 deepSeekInstance:
 type: aws:ec2:Instance
 properties:
 ami: ${amiId}
 instanceType: "g4dn.xlarge"
 keyName: ${deepSeekKey.keyName}
 rootBlockDevice:
 volumeSize: 100
 volumeType: gp3
 subnetId: ${deepSeekSubnet.id}
 vpcSecurityGroupIds:
 - ${deepSeekSecurityGroup.id}
 iamInstanceProfile: ${deepSeekProfile.name}
 userData: ${userData}
 tags:
 Name: deepSeek-server

outputs:
 AmiId: ${amiId}
 InstanceId: ${deepSeekInstance.id}
 InstancePublicDns: ${deepSeekInstance.publicIp}

Step 4: Install Ollama via cloud-init

The EC2 instance is a blank box until cloud-init runs. The user-data script below installs the NVIDIA GRID drivers, Docker, and the NVIDIA Container Toolkit, then starts the Ollama and Open WebUI containers. To switch models, edit the ollama run line—the rest is identical regardless of which model you want.

#cloud-config
users:
- default

package_update: true

packages:
- apt-transport-https
- ca-certificates
- curl
- openjdk-17-jre-headless
- gcc

runcmd:
- yum install -y gcc kernel-devel-$(uname -r)
- aws s3 cp --recursive s3://ec2-linux-nvidia-drivers/latest/ .
- chmod +x NVIDIA-Linux-x86_64*.run
- /bin/sh ./NVIDIA-Linux-x86_64*.run --tmpdir . --silent
- touch /etc/modprobe.d/nvidia.conf
- echo "options nvidia NVreg_EnableGpuFirmware=0" | sudo tee --append /etc/modprobe.d/nvidia.conf
- yum install -y docker
- usermod -a -G docker ec2-user
- systemctl enable docker.service
- systemctl start docker.service
- curl -s -L https://nvidia.github.io/libnvidia-container/stable/rpm/nvidia-container-toolkit.repo | sudo tee /etc/yum.repos.d/nvidia-container-toolkit.repo
- yum install -y nvidia-container-toolkit
- nvidia-ctk runtime configure --runtime=docker
- systemctl restart docker
- docker run -d --gpus=all -v ollama:/root/.ollama -p 11434:11434 --name ollama --restart always ollama/ollama
- sleep 120
- docker exec ollama ollama run deepseek-r1:7b
- docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main

You might also like:

Step 5: Deploy the infrastructure

Make sure your AWS credentials are configured:

aws configure

Pulumi supports several other authentication methods for the AWS provider. Once credentials are in place, deploy the infrastructure:

pulumi up

Pulumi previews the changes; type yes to confirm.

pulumi up
Please choose a stack, or create a new one: <create a new stack>
Please enter your desired stack name.
To create a stack in an organization, use the format <org-name>/<stack-name> (e.g. `acmecorp/dev`): dev
Please enter your desired stack name.
Created stack 'dev'
Previewing update (dev)
View in Browser (Ctrl+O): https://app.pulumi.com/dirien/deepseek-ollama-typescript/dev/previews/1dbb18ea-ba31-4d5b-9510-5dce19eb8ee8
Type Name Plan
+ pulumi:pulumi:Stack deepseek-ollama-typescript-dev create
+ ├─ aws:ec2:KeyPair deepSeekKey create
+ ├─ aws:ec2:Vpc deepSeekVpc create
+ ├─ aws:iam:Role deepSeekRole create
+ ├─ aws:iam:InstanceProfile deepSeekProfile create
+ ├─ aws:ec2:SecurityGroup deepSeekSecurityGroup create
+ ├─ aws:ec2:RouteTable deepSeekRouteTable create
+ ├─ aws:ec2:InternetGateway deepSeekInternetGateway create
+ ├─ aws:ec2:Subnet deepSeekSubnet create
+ ├─ aws:iam:RolePolicyAttachment deepSeekS3Policy create
+ ├─ aws:ec2:RouteTableAssociation deepSeekRouteTableAssociation create
+ └─ aws:ec2:Instance deepSeekInstance create
Outputs:
amiId : "ami-085131ff43045c877"
instanceId : output<string>
instancePublicDns: output<string>
Resources:
+ 12 to create
Do you want to perform this update? yes
Updating (dev)
View in Browser (Ctrl+O): https://app.pulumi.com/dirien/deepseek-ollama-typescript/dev/updates/1
Type Name Status
+ pulumi:pulumi:Stack deepseek-ollama-typescript-dev created (40s)
+ ├─ aws:ec2:KeyPair deepSeekKey created (0.47s)
+ ├─ aws:iam:Role deepSeekRole created (1s)
+ ├─ aws:ec2:Vpc deepSeekVpc created (12s)
+ ├─ aws:iam:InstanceProfile deepSeekProfile created (6s)
+ ├─ aws:iam:RolePolicyAttachment deepSeekS3Policy created (0.90s)
+ ├─ aws:ec2:InternetGateway deepSeekInternetGateway created (0.69s)
+ ├─ aws:ec2:Subnet deepSeekSubnet created (11s)
+ ├─ aws:ec2:SecurityGroup deepSeekSecurityGroup created (2s)
+ ├─ aws:ec2:RouteTable deepSeekRouteTable created (1s)
+ ├─ aws:ec2:RouteTableAssociation deepSeekRouteTableAssociation created (0.92s)
+ └─ aws:ec2:Instance deepSeekInstance created (12s)
Outputs:
amiId : "ami-085131ff43045c877"
instanceId : "i-0ae7495781ace3e81"
instancePublicDns: "18.159.211.136"
Resources:
+ 12 created
Duration: 42s

The infrastructure provisions in under a minute, but the cloud-init script needs another 5–10 minutes to install drivers, pull container images, and download the model weights. SSH in to watch the progress, or just wait and load the Web UI when it’s ready.

ssh -i deepseek.pem ec2-user@<instance-public-ip>

Check the container status:

sudo docker ps
CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES
c8714335e205 ghcr.io/open-webui/open-webui:main "bash start.sh" 6 minutes ago Up 6 minutes (healthy) 0.0.0.0:3000->8080/tcp, :::3000->8080/tcp open-webui
bf4bb3b7ede1 ollama/ollama "/bin/ollama serve" 8 minutes ago Up 7 minutes 0.0.0.0:11434->11434/tcp, :::11434->11434/tcp ollama
[ec2-user@ip-10-0-58-122 ~]$

Step 6: Access the Web UI or API

Once the containers are healthy, open http://<instance-public-ip>:3000 in your browser for Open WebUI:

Open WebUI is not secured by default. Restrict the security group to your IP, put it behind an authenticated proxy, or terminate TLS at an ALB before exposing it to the internet.

For programmatic access, Ollama exposes an OpenAI-compatible API on port 11434. Most clients written for the OpenAI SDK only need a base-URL change:

from openai import OpenAI

client = OpenAI(
 base_url="http://<instance-public-ip>:11434/v1",
 api_key="ollama", # required by the SDK, ignored by Ollama
)

response = client.chat.completions.create(
 model="llama3.1:8b",
 messages=[{"role": "user", "content": "Why is the sky blue?"}],
)
print(response.choices[0].message.content)

Deploy GPU infrastructure with Pulumi

Provision the GPU EC2 instance, network, and IAM role for your self-hosted LLM in one program, then switch models with a single config change.

Get started

How do I switch models?

Ollama hosts every major open-weight family in its model library. Pulling a different model is two commands inside the EC2 instance—or a one-line edit to the cloud-init script if you want it provisioned automatically:

# DeepSeek-R1 distill (default in this guide)
docker exec ollama ollama run deepseek-r1:7b

# Llama 3.1 (Meta, 8B)
docker exec ollama ollama run llama3.1:8b

# Qwen 2.5 (Alibaba, 7B)
docker exec ollama ollama run qwen2.5:7b

# Mistral (7B)
docker exec ollama ollama run mistral:7b

# Larger reasoning model (needs g5.2xlarge or larger)
docker exec ollama ollama run deepseek-r1:32b

Tags follow a <size> or <size>-<quantization> pattern—8b, 8b-instruct-q4_K_M, 8b-instruct-q8_0. Q4 is the default and the right starting point; bump to Q8 only if you have spare VRAM and notice quality issues with Q4. Browse the full tag list for any model on its Ollama library page.

Cleaning up

When you’re done, tear everything down:

pulumi destroy

What are the next steps?

You now have a reproducible, IaC-managed deployment of any open-source LLM on AWS. The infrastructure is fixed; the model is a parameter. From here, the natural extensions are wiring this up to a real application, adding RAG over your own data, or moving the deployment behind an authenticated load balancer.

If you want to go further with AI on Pulumi, here are some related guides:

Deploy LangServe Apps with Pulumi on AWS (RAG & Chatbot) — Build a retrieval-augmented chatbot that could front-end this Ollama instance.
Deploy AI Models on Amazon SageMaker using Pulumi Python IaC — A SageMaker alternative when you’d rather not manage the EC2 host yourself.
Build an AI Slack Bot on AWS Using Embedchain & Pulumi — Wire an LLM into Slack as an internal assistant.
What is Infrastructure as Code? — Background on the IaC approach used throughout this guide.

Try Pulumi for Free

Changelog

2026-04-30 — Broadened scope from DeepSeek-only to any Ollama-supported model (Llama, Qwen, Mistral). Added TL;DR, instance-type recommendation table, cost-vs-hosted-API comparison, and HowTo structured data. Restructured headings as user questions. Verified Ollama and cloud-init commands against current versions.
2025-03-10 — Minor edits and corrections.
2025-01-27 — Original post: Run DeepSeek-R1 on AWS EC2 Using Ollama.

Deploy AI Models on Amazon SageMaker using Pulumi Python IaC

Kat Morgan — Mon, 11 Sep 2023 00:00:00 +0000

Running models from Hugging Face on Amazon SageMaker is a popular deployment option for AI/ML services. While the SageMaker console allows for provisioning these cloud resources, this deployment pattern is labor intensive to document and vulnerable to human errors when reproducing as a regular operations practice. Infrastructure as Code (IaC) offers a reliable and easy to duplicate deployment practice. By developing this IaC with Pulumi, practitioners can choose to write their infrastructure code in Python and seamlessly develop both AI application code and IaC code in the same language.

In this short tutorial we will deploy a publicly available Meta AI LlaMa 2 based model from Hugging Face, on Amazon SageMaker. Then we will test it with a natural language prompt using a short Python script.

Pulumi makes AI/ML Easy?

We will use the sagemaker-aws-python Pulumi Template to bootstrap our Python SageMaker IaC. Templates allow you to quickly bootstrap new Pulumi projects from a working scaffold which you can then customize further to your needs. Out of the box, this template provisions Amazon IAM Roles to assign SageMaker privileges, CloudWatch alarms to alert in case of latency or error spikes for the endpoint, and of course a Meta AI LlaMa 2 based LLM (NousResearch/Llama-2-7b-chat-hf) hosted on Hugging Face.

Requirements

Instructions

Let’s begin by logging into Pulumi Cloud:

# There are many ways to store Pulumi state, here we use Pulumi Cloud
# Other state backends include S3, local file, and more
pulumi login

If you’re unsure of which Pulumi state backend you’re using, you can check by running pulumi whoami (or pulumi whoami -v for more info).

2. Prepare a new Pulumi project

Here we create our new Pulumi project directory and populate it from the sagemaker-aws-python Pulumi template

# Create a new directory & change directories into it
mkdir newSageMaker && cd newSageMaker

# Start your project from the sagemaker-aws-python template
# Follow along with the prompts to create your new project and initialize a stack
pulumi new sagemaker-aws-python

While creating a new project from the sagemaker-aws-python Pulumi template, you will be prompted for a project name, description, stack name, and Amazon Web Service Region. You can proceed with defaults, or supply your own.

After responding to all prompts, the pulumi new command will proceed to setup a Python Virtual Environment (venv) and download all dependencies into the venv.

3. Deploy your model as a new SageMaker endpoint

This step may take between 10 and 20 minutes while Amazon builds your infrastructure and deploys the configured model. You can follow along in the console as resources are provisioned, or open the link displayed in terminal to view the deployment status and other stack information in Pulumi Cloud.

pulumi up

4. Try your new SageMaker endpoint

Once your stack has finished deploying, use this rudimentary Python snippet to test the deployed SageMaker endpoint.

NOTE: Notice that we are using us-east-1 in this script. Be sure to change the region in Python to match the region you deployed the SageMaker endpoint into.

First, save the following python snippet as test.py:

import json, boto3, argparse

def main(endpoint_name):
 client = boto3.client('SageMaker-runtime', region_name='us-east-1')
 payload = json.dumps({"inputs": "In 3 words, name the biggest mountain on earth?"})
 response = client.invoke_endpoint(EndpointName=endpoint_name, ContentType="application/json", Body=payload)
 print("Response:", json.loads(response['Body'].read().decode()))

if __name__ == "__main__":
 parser = argparse.ArgumentParser()
 parser.add_argument("endpoint_name")
 main(parser.parse_args().endpoint_name)

Once you have the test.py script created, source the Python virtual environment named venv (created automatically by Pulumi) and run the script using the name of your new endpoint, taken directly from the Pulumi stack output:

# Source the venv
# On Linux & MacOS
source venv/bin/activate

# Execute test.py
python3 test.py $(pulumi stack output EndpointName)

5. Cleanup all resources

Finally, when you’re finished with testing your Hugging Face model on SageMaker, you can easily clean up un-used resources with one easy command.

pulumi destroy

Conclusion

To recap, in a few commands, we created a new Pulumi Python project from a ready-to-roll template, deployed an LLM endpoint on Amazon SageMaker, and tested it with a short Python script to generate a response from our model!

AI and ML is rapidly becoming a necessity with every new day. It may appear daunting or out of reach at first glance, but with the power of IaC written as Pulumi Python programs, getting started has never been easier.

If you followed along then tell us how it worked out for you! We would love to know what you are looking forward to, or if you have ideas for future installments of the Pulumi Python #PulumiMLOps series!

Join us on Twitter, and on the Pulumi Community Slack to decide what #PulumiMLOps we take on next!

The Real AI Challenge is Cloud, not Code!

Kat Morgan — Wed, 30 Aug 2023 00:00:00 +0000

The AI industry is stealing the show as tech’s goldrush of the ’20s. Just looking at ChatGPT’s record setting user growth, and rapid 3rd party integration by top brands, it is not surprising the hype suggests this is the beginning of a major digital transformation.

However, using AI/ML in your own products has some major challenges and obstacles. Below is a diagram of the end to end workflow of building and using an AI model: preparing the data, training a model, fine-tuning a model, hosting and running a model, building a backend service to serve the model, and building the user interface that interacts with the model. Most AI engineers are only involved in a few steps of the process. However, there is one challenge that is common across the entire workflow: creating and managing the cloud infrastructure is hard.

Figure 1. A sneak peak at the map of ML development and product path

Training a model requires spinning up hyper scale GPU clusters. Preparing and consuming the training or fine-tuning data requires managing data warehouses and buckets of object storage. Building an AI backend service requires packaging the model, deploying and scaling the model across compute infrastructure, creating and managing the network infrastructure like load balancing, and managing the vector databases. Building great frontend user experiences requires provisioning and managing CDNs and web application services. Suffice to say: The most difficult challenge that we face with AI today is a problem of cloud orchestration.

Most of this cloud orchestration today is done manually or with complex scripts. This is usually fraught with errors and simply doesn’t scale. Too much time is spent making cloud infrastructure work instead of focusing on actual AI/ML tasks. Infrastructure as code (IaC) is a key component to solving the cloud orchestration challenge present in AI/ML. By applying the rigor and precision of software development practices to cloud operations, IaC offers AI/ML professionals an efficient, reliable, and predictable way to develop at the highest velocity. Pulumi is an open source infrastructure as code platform that allows engineers to use any programming languages, including Python, to provision and manage AI infrastructure.

This blog post is the first installment of a series on AI Infrastructure as Python. We will start this journey with building an AI backend service for a chatbot. In this post, we will deploy a LLM model behind an API backend running on compute infrastructure in the cloud. This entire infrastructure pipeline will be deployed using IaC written in Python. The series will follow this AI backend service through its evolution into a robust and resilient cloud native service.

The most difficult challenge that we face with AI today is a problem of cloud orchestration

Before we get into the details of using Pulumi to deploy a private LlaMa 2 API chatbot service—in 30 minutes or less, of course—let’s start with some quick terminology/context:

Katwalk Server is a demo AI application written to host your choice of LLM either locally or in the cloud, and serve it as an OpenAI API compatible service. As a practical, hands-on introduction to IaC for the MLOps space, this project aims to demystify the concepts and showcase the benefits Pulumi can bring to your AI/ML projects.
Large Language Models or LLMs (like ChatGPT) are machine learning models trained to generate human-like conversational text which have already become essential tools for businesses and individuals, transforming every day tasks and how we interact with technology.
LlaMa is an LLM created by Meta, available for free for research and commercial use.

Figure 2. Or just let ChatGPT describe itself

Deploy a private LlaMa 2 API chatbot service … in 30 minutes or less!

If you are ready to try the #MLOpsChallenge along with us, then let’s double check a few requirements before starting the clock on our 30 minute chatbot challenge. While Pulumi supports many languages, we chose Python for this project, as Python is a familiar language in the AI industry.

Requirements

Choose one of the following deployment platforms. (You can actually choose more than one, if you’d like!)

Now, for the real fun, let’s start the timer and deploy our own chatbot! Note that the instructions below are for Runpod; instructions for the other two deployment platforms are found in the GitHub repository.

1. Prepare your Pulumi IaC directory

First we need to clone our IaC repository from GitHub and prepare our Python environment.

# Clone the repository and cd to the pulumi iac directory
git clone https://github.com/pulumiverse/katwalk && cd katwalk/pulumi

# Create and initialize the python virtual env
python3 -m venv venv && source venv/bin/activate

# Install python dependencies
python3 -m pip install -r requirements.txt

Next, let’s setup our state and secrets store in Pulumi Cloud.

# There are many ways to store Pulumi state, here we use Pulumi Cloud
# Other state backends include S3, local file, and more
pulumi login

# Initialize your stack
# Here we name the stack "dev"
pulumi stack init --stack dev

3. Configure required credentials

Configure your Huggingface credentials. If you open the Pulumi.${stackName}.yaml file, you can see the encrypted secrets in this plain text YAML configuration.

# Set Huggingface.co username
pulumi config set hfUsername <huggingface_username>

# Configure token as secret
pulumi config set --secret hfToken <huggingface_api_token>

# Set the model that you want to download
pulumi config set hfModel "meta-llama/Llama-2-7b-chat-hf"

4. Deploy in the cloud on Runpod.io

While there are three providers already supported in this codebase, this post illustrates deploying to Runpod.io, a GPU and ML dedicated cloud catering to AI workloads and development tasks.

# This enables the IaC to deploy Katwalk Server
pulumi config set deploy True

# Set the deploy runtime to runpod to deploy on the Runpod cloud
pulumi config set runtime runpod

# Configure your Runpod API Token as a secure Pulumi secret
# API token available at https://www.runpod.io/console/user/settings
pulumi config set --secret runpodToken <your_runpod_api_token>

# Finally, run `pulumi up` to deploy!
pulumi up

# When done, you can 'destroy' the stack to deprovision your deployment
pulumi destroy

There’s currently a bug in the code that does not return the fully-qualified domain name (FQDN) from Runpod for your chatbot instance. To get the FQDN (referenced later in this post as RUNPOD_FQDN), you’ll need to log into Runpod and retrieve that information.

5. Build the Katwalk container

While there are many other ways to orchestrate ML services in the cloud and locally, in this project we are taking ownership of the full application and infrastructure story. In fact, all three supported providers use the same container image to serve the LlaMa LLM API Service, and you can build it yourself just like this:

# Set image build to True
pulumi config set imageBuild True

# Let's build this without pushing to a registry for now
pulumi config set imagePush False

# Give your katwalk image a project name
pulumi config set registryProject $(whoami)

# Now build the image!
pulumi up

6. Talk to your chatbot!

Once your Katwalk LlaMa server is running, you can interact with the API by sending prompts as a JSON payload. In future posts we will orchestrate a chat frontend for our chatbot but for now we’ll use a curl command. You can also substitute an API developer tool such as Postman or Insomnia!

# send a prompt with curl
curl -s -X 'POST' 'http://${RUNPOD_FQDN}/v1/chat' -H 'accept: application/json' -H 'Content-Type: application/json' -d '{"prompt": "Write a short story about a robot."}'
{
 "text": [
 "\nOnce upon a time, there was a little robot named R2. R2 was a friendly and curious robot who lived in a big city. One day, R2 decided to go on an adventure. He set out to explore the city and learn about all the different things he could see and do.\nAs R2 explored the city, he met all kinds of people. Some were kind and welcoming, while others were scared or suspicious of him. Despite this, R2 continued to be friendly and curious, always asking questions and trying to learn more about the world around him.\nOne day, while R2 was exploring a busy market, he saw a group of people gathered around a little girl who was"
 ]
}

Figure 3. A prompt and response from meta-llama/Llama-2-7b-chat-hf hosted on Katwalk Server

In a world where “data is the new black gold” and tokens are money, deploying a chatbot in 30 minutes is not just interesting, it is a novel capability quickly becoming a necessity.

Platform engineering, DevOps, or MLOps may be the next hardest step in building the AI future. Pulumi offers a reliable path to higher velocity AI App development and MLOps. Together with Python-based IaC, it empowers the MLOps community to build equity in common AI platform code, and share IaC in a familiar language.

If you followed along then tell us how it worked out for you! We would love to know what you are looking forward to, or if you have ideas for future installments of the Pulumi Python + MLOps series!

Join us in the Pulumi Community Slack or in the Pulumiverse Community Katwalk Github repository to decide what #aiChallenge we tackle next!

Figure 4. Midjourney generated image of an imagined machine learning research engineer working among cables, computers, keyboards, and screens, in the glow of electronic lights. Image was generated from a prompt ~80% produced by ChatGPT based on this blog post content and a few superficial details about the author

Pulumi Blog: Llama

Run Open-Source LLMs on AWS EC2 with Ollama and Pulumi

Why run open-source LLMs on AWS EC2?

Which models can I run, and which EC2 instance do I need?

How much does this cost vs. hosted APIs?

How do I deploy Ollama on AWS EC2 with Pulumi?

Prerequisites

What is Ollama?

Architecture

Create a new Pulumi project

Step 1: Create an instance role with S3 access

Step 2: Create the network

Step 3: Launch the GPU EC2 instance

Step 4: Install Ollama via cloud-init

Step 5: Deploy the infrastructure

Step 6: Access the Web UI or API

How do I switch models?

Cleaning up

What are the next steps?

Changelog

Deploy AI Models on Amazon SageMaker using Pulumi Python IaC

Pulumi makes AI/ML Easy?

Requirements

Instructions

1. Login to Pulumi Cloud and initialize stack

2. Prepare a new Pulumi project

3. Deploy your model as a new SageMaker endpoint

4. Try your new SageMaker endpoint

5. Cleanup all resources

Conclusion

The Real AI Challenge is Cloud, not Code!

The most difficult challenge that we face with AI today is a problem of cloud orchestration

Deploy a private LlaMa 2 API chatbot service … in 30 minutes or less!

Requirements

1. Prepare your Pulumi IaC directory

2. Login to Pulumi Cloud and initialize stack

3. Configure required credentials

4. Deploy in the cloud on Runpod.io

5. Build the Katwalk container

6. Talk to your chatbot!