Tagged in

Mlops

Decoding ML

Battle-tested content on designing, coding, and deploying production-grade ML & MLOps systems. The hub for continuous learning on ML system design, ML engineering, MLOps, large language models (LLMs), and computer vision (CV).

More information

Followers

858

Elsewhere

More, on Medium

Mlops

Vesa Alexandru in Decoding ML

May 10

LLM TWIN COURSE: BUILDING YOUR PRODUCTION-READY AI REPLICA

Notes

Fix your messy ML configs in your Python projects

2024 MLOps learning roadmap…

Paul Iusztin in Decoding ML

Mar 16

An End-to-End Framework for Production-Ready LLM Systems by Building Your LLM Twin

12 responses

Paul Iusztin in Decoding ML

Mar 15

Learn an end-to-end framework for production-ready LLM systems by building your LLM twin

1 response

Paul Iusztin in Decoding ML

Mar 1

Notes

4 key decoding strategies for LLMs that you must know

The only 6 prompt…

Alex Razvant in Decoding ML

Feb 7

Deploying Deep Learning Models at Scale — Triton Inference Server 0 to 100

Prepare and deploy an Image…

3 responses

Paul Iusztin in Decoding ML

Feb 3

The Hands-On LLMs Series

Prepare your RAG LangChain application for production

Paul Iusztin in Decoding ML

Jan 30

The Hands-On LLMs Series

Design a RAG LangChain application leveraging the 3-pipeline architecture

LLM TWIN COURSE: BUILDING YOUR PRODUCTION-READY AI REPLICA

The Role of Feature Stores in Fine-Tuning…

Master ML configuration files using OmegaConf and Hydra

How to ensure your deep learning stack is fail-safe in production?

Notes

Fix your messy ML configs in your Python projects

2024 MLOps learning roadmap…

An End-to-End Framework for Production-Ready LLM Systems by Building Your LLM Twin

Learn an end-to-end framework for production-ready LLM systems by building your LLM twin

Notes

4 key decoding strategies for LLMs that you must know

The only 6 prompt…

Deploying Deep Learning Models at Scale — Triton Inference Server 0 to 100

Prepare and deploy an Image…

The Hands-On LLMs Series

Prepare your RAG LangChain application for production

The Hands-On LLMs Series

Design a RAG LangChain application leveraging the 3-pipeline architecture