When you enroll in this course, you'll also be enrolled in this Specialization.
Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate
There are 4 modules in this course
Do you aspire to be a Rust developer at the forefront of the AI revolution? This groundbreaking course is designed specifically to train you in Large Language Model Operations (LLMOps) using Rust. This course doesn't just scratch the surface; it takes a deep dive into how you can integrate Rust with sophisticated LLM frameworks like HuggingFace Transformers. We'll also explore how to effectively deploy these large models on cloud infrastructures such as AWS, all while incorporating DevOps methodologies tailored for LLMOps.
Do you aspire to be a Rust developer at the forefront of the AI revolution? This groundbreaking 4-week course is designed specifically to train you in Large Language Model Operations (LLMOps) using Rust. This course doesn't just scratch the surface; it takes a deep dive into how you can integrate Rust with sophisticated LLM frameworks like HuggingFace Transformers. We'll also explore how to effectively deploy these large models on cloud infrastructures such as AWS, all while incorporating DevOps methodologies tailored for LLMOps.
What's included
23 videos16 readings1 assignment2 ungraded labs
Show info about module content
23 videos•Total 87 minutes
Instructor Intro•1 minute
A Function, the Essence of Programming•7 minutes
Operationalize Microservices•2 minutes
Continuous Integration for Microservices•7 minutes
What is Makefile and how do you use it?•3 minutes
What is DevOps?•2 minutes
Kaizen methodology•4 minutes
Infrastructure as Code for Continuous Delivery•3 minutes
Responding to Compromised Resources and Workloads•4 minutes
Designing and Implementing Monitoring and Alerting•2 minutes
Audit Network Security•1 minute
Rust Secure by Design•5 minutes
Preventing Data Races with Rust Compiler•3 minutes
Using AWS Config for Security•4 minutes
AWS Security Hub Demo•4 minutes
Explain How to Secure Your Account with 2FA•3 minutes
Understanding Access Permissions•4 minutes
Repository Permission Levels Explained•3 minutes
Repository Privacy Settings and Options•3 minutes
Unveiling Key Concepts of the GitHub Ecosystem•4 minutes
Demo: Implementing GitHub Actions•4 minutes
Demo: GitHub Codespaces•6 minutes
Demo: GitHub Copilot•8 minutes
16 readings•Total 160 minutes
Source Code Resources•10 minutes
Infrastructure as code•10 minutes
Continuous integration•10 minutes
Continuous delivery•10 minutes
Automation and tooling•10 minutes
Report a problem with the course•10 minutes
Shared responsibility
•10 minutes
Identity and access management•10 minutes
Infrastructure protection•10 minutes
Incident response•10 minutes
External Lab: Use GitHub Actions and Codespaces•10 minutes
About two-factor authentication•10 minutes
Access permissions on GitHub•10 minutes
About Continuous Integration•10 minutes
About continuous deployment•10 minutes
Final Week-Reflections•10 minutes
1 assignment•Total 30 minutes
DevOps Concepts for MLOps•30 minutes
2 ungraded labs•Total 120 minutes
Lab: Using a Makefile with Rust•60 minutes
Lab: Preventing Data Races in Rust•60 minutes
Rust Hugging Face Candle
Module 2•4 hours to complete
Module details
This week, you will delve into the powerful combination of Rust with Candle, a minimalist ML framework, and explore how they can be used with Hugging Face's popular transformer models. You will apply these concepts by working on a series of hands-on labs that guide you through building, training, and deploying machine learning models using Rust, Candle, and Hugging Face. The assessment will challenge you to create a real-world application using these tools, demonstrating your ability to apply the techniques learned in complex scenarios.
What's included
15 videos16 readings1 assignment
Show info about module content
15 videos•Total 51 minutes
Candle: A Minimalist ML Framework for Rust•3 minutes
Using GitHub Codespaces for GPU Inference with Rust Candle•6 minutes
VSCode Remote SSH development AWS Accelerated Compute•5 minutes
Building Hello World Candle•3 minutes
Exploring StarCoder: A State-of-the-Art LLM •6 minutes
Using Whisper with Candle to Transcribe•6 minutes
Exploring Remote Dev Architectures on AWS•2 minutes
Advantages of Rust for LLMs•2 minutes
Serverless Inference•2 minutes
Rust CLI Inference•2 minutes
Rust Chat Inference•2 minutes
Continuous Build of Binaries for LLMOps•2 minutes
Chat Loop for StarCoder•2 minutes
Invoking Rust Candle on AWS G5-Part One•5 minutes
Invoking BigCode on AWS G5-Part Two•3 minutes
16 readings•Total 160 minutes
rust-candle-demos•10 minutes
Configuring NVIDIA CUDA for your codespace•10 minutes
Getting Started Candle•10 minutes
Candle Examples•10 minutes
External Lab: Candle Hello World•10 minutes
External Lab: Run an LLM with Candle•10 minutes
Developer Guide cuDNN•10 minutes
cuDNN Webinar•10 minutes
Programming Tensor Cores in CUDA 9•10 minutes
Tensor Ops Made Easier in cuDNN•10 minutes
External Lab: Using BigCode to Assist With Coding•10 minutes
StarCoder: A State-of-the-Art LLM for Code•10 minutes
Falcon LLM•10 minutes
Whisper LLM•10 minutes
Candle Structure•10 minutes
Final Week Reflection•10 minutes
1 assignment•Total 30 minutes
Rust Hugging Face Candle•30 minutes
Key LLMOps Technologies
Module 3•3 hours to complete
Module details
This week, you will learn how to implement state-of-the-art natural language processing models in Rust using key LLMOps technologies like Rust Bert, tch-rs, and ONNX. You will apply these skills by converting a BERT model to ONNX and deploying it in a Rust application, demonstrating proficiency in operationalizing NLP pipelines.
What's included
10 videos13 readings1 assignment
Show info about module content
10 videos•Total 32 minutes
Introduction to Rust Bert•2 minutes
Installation and Setup•6 minutes
Basic Syntax and Model Loading•2 minutes
Building a sentiment analysis CLI•4 minutes
Introduction to Rust PyTorch•2 minutes
Running a PyTorch Hello World•2 minutes
PyTorch Pretrained•4 minutes
Running PyTorch Pretrained•7 minutes
Introduction to ONNX•1 minute
ONNX Conversions•2 minutes
13 readings•Total 130 minutes
Getting Started Rust Bert•10 minutes
External Lab: Translate a Spanish song to English
•10 minutes
Rust Bert pipelines•10 minutes
ONNX Support Rust Bert•10 minutes
Loading pretrained and custom model weights•10 minutes
External Lab: Run a Pretrained model•10 minutes
Rust bindings for PyTorch•10 minutes
ONNX Concepts•10 minutes
ONNX with Python•10 minutes
Converters•10 minutes
ONNX Model Hub•10 minutes
Final Week-Reflections•10 minutes
External Lab: Use ONNX•10 minutes
1 assignment•Total 30 minutes
Using Rust Bert•30 minutes
Key Generative AI Technologies
Module 4•3 hours to complete
Module details
This week, you will learn to utilize GenAI Systems to enhance your ability to write production software and solve problems.
What's included
12 videos8 readings2 assignments
Show info about module content
12 videos•Total 68 minutes
Extending Google Bard•4 minutes
Exploring Google Colab with Bard•4 minutes
Exploring Colab AI•5 minutes
Exploring Gen App Builder•2 minutes
Responsible AI with AWS Bedrock•5 minutes
AWS Bedrock with Claude•8 minutes
Summarizing text with Claude
•5 minutes
Using the AWS Bedrock API•2 minutes
Live Coding AWS CodeWhisperer Part One•6 minutes
Live Coding AWS CodeWhisperer Part Two•14 minutes
Live Coding AWS CodeWhisperer Part Three•8 minutes
Using AWS CodeWhisperer CLI•4 minutes
8 readings•Total 80 minutes
Bard FAQ•10 minutes
External Lab: Build a plot with Colab AI•10 minutes
External Lab: AWS Bedrock•10 minutes
AWS Cloud Adoption Framework for Artificial Intelligence, Machine Learning, and Generative AI•10 minutes
People perspective: Culture and change towards AI/ML-first•10 minutes
External Lab: Use CodeWhisperer for Rust Calculator•10 minutes
Share your learning experience•10 minutes
Next Steps•10 minutes
2 assignments•Total 60 minutes
Key LLMOps Technologies•30 minutes
Final-Quiz•30 minutes
Earn a career certificate
Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.
Duke University has about 13,000 undergraduate and graduate students and a world-class faculty helping to expand the frontiers of knowledge. The university has a strong commitment to applying knowledge in service to society, both near its North Carolina campus and around the world.
When will I have access to the lectures and assignments?
To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
What will I get if I subscribe to this Specialization?
When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.
Is financial aid available?
Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.