Decoding ML Newsletter

Home
LLM & RAG Open Source Course
LLM Engineer's Handbook
Archive
About
Decoding ML Newsletter
Decoding ML Newsletter
Join for battle-tested content on designing, coding, and deploying production-grade ML & MLOps systems. Every week. For FREE.

Recent posts

View all
The ultimate LLM fine-tuning pipeline
Master production-ready fine-tuning with AWS SageMaker, Unsloth, and MLOps best practices
 • 
Paul Iusztin
Connecting the dots in data and AI systems
Simplifying MLE & MLOps with the FTI Architecture
 • 
Paul Iusztin
4
ML serving 101: Core architectures
Choose the right architecture for your AI/ML app
 • 
Paul Iusztin
The ABCs of Diffusion Models
Your Guide to ML’s Next Big Thing
 • 
Anca Ioana Muscalagiu
Also on
GitHub
Medium
LinkedIn
X
Books
LLM Engineer's Handbook
Master the art of engineering Large Language Models from concept to production
Open source
LLM Twin Course
Build a production-ready LLM & RAG system

ml-system-design

View all
ML serving 101: Core architectures
Choose the right architecture for your AI/ML app
 • 
Paul Iusztin
Build a semantic news search engine with 0 delay
How to build a real-time news search engine using Kafka, vector DBs, RAG and streaming engines.
 • 
Paul Iusztin
Real-time feature pipelines for RAG
RAG hybrid search with transformers-based sparse vectors. CDC tech stack for event-driven architectures.
 • 
Paul Iusztin
Building ML systems the right way using the FTI architecture
The fundamentals of the FTI architecture that will help you build modular and scalable ML systems using MLOps best practices.
 • 
Paul Iusztin
The LLM-Twin Free Course on Production-Ready RAG applications.
Learn how to build a full end-to-end LLM & RAG production-ready system, follow and code along each component by yourself.
 • 
Alex Razvant

mlops

View all
The 6 MLOps foundational principles
The core MLOps guidelines for production ML
 • 
Paul Iusztin
2
Experiment Tracking Essentials: Finding the Right Tool
Gradio’s Custom Dashboards vs Wandb’s Built-In Tools for Training Diffusion Models
 • 
Anca Ioana Muscalagiu
The LLM-Twin Free Course on Production-Ready RAG applications.
Learn how to build a full end-to-end LLM & RAG production-ready system, follow and code along each component by yourself.
 • 
Alex Razvant
Architect scalable and cost-effective LLM & RAG inference pipelines
Design, build and deploy RAG inference pipeline using LLMOps best practices.
 • 
Paul Iusztin
CDC: Enabling Event-Driven Architectures
Transforming Data Streams: The Core of Event-Driven Architectures
 • 
Vesa Alexandru
1

machine-learning-engineering

View all
Reduce your PyTorch code latency by 82%
How not to optimize the inference of your DL models. Computer science is dead.
 • 
Paul Iusztin
2
The 4 Advanced RAG Algorithms You Must Know to Implement
Implement from scratch 4 advanced RAG methods to optimize your retrieval and post-retrieval algorithm
 • 
Paul Iusztin
1
SOTA Python Streaming Pipelines for Fine-tuning LLMs and RAG - in Real-Time!
Use a Python streaming engine to populate a feature store from 4+ data sources
 • 
Paul Iusztin
CDC: Enabling Event-Driven Architectures
Transforming Data Streams: The Core of Event-Driven Architectures
 • 
Vesa Alexandru
1

generative-ai

View all
The ultimate LLM fine-tuning pipeline
Master production-ready fine-tuning with AWS SageMaker, Unsloth, and MLOps best practices
 • 
Paul Iusztin
Connecting the dots in data and AI systems
Simplifying MLE & MLOps with the FTI Architecture
 • 
Paul Iusztin
4
The ABCs of Diffusion Models
Your Guide to ML’s Next Big Thing
 • 
Anca Ioana Muscalagiu
Inside vector DBs: A simple guide
Understand the fundamentals of vector databases
 • 
Paul Iusztin
4
Instagram data mining using LLMs
Crawl Instagram posts and use LLMs to extract critical insights for business growth.
 • 
Vlad Adumitracesei
6

deep-learning

View all
Embeddings: the cornerstone of AI & ML
Fundamentals of embeddings: what they are, how they work, why they are so powerful and how they are created.
 • 
Paul Iusztin
A Kickstart in Deep Learning Real-Time Video Processing
Working with video data in ML. Streaming video through HTTP, WebSockets, WebRTC with Python. A kick-start towards vision ML.
 • 
Alex Razvant
Your model takes too long to do inference?
Compiling ML models. Optimizing to run in C++/Java/C#. Fastest Inference Engine out there.
 • 
Alex Razvant
5 Tools to monitor the performance of your Deep Learning Stack!
What are DML Notes and a curated view on Popular Vision Foundation Models, toolset to use in vision data-engineering and performance monitoring…
 • 
Alex Razvant
DML: How to build a PyTorch - TensorRT pipeline for YOLO Object Detection Models!
Practical tutorial on how to automate targeted GPU optimizations for YOLOv5,YOLOv8 models.
 • 
Alex Razvant
4

data-engineering

View all
Instagram data mining using LLMs
Crawl Instagram posts and use LLMs to extract critical insights for business growth.
 • 
Vlad Adumitracesei
6
© 2024 Paul Iusztin
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great culture