Machine Learning

Artificial Intelligence

Large Language Models

Inference

Explore recommended reads, summarized by AI

Large Language Model Inference

Technical writing on how LLMs generate responses and how to optimize their deployment.

Deploying and Optimizing LLM Inference

How LLMs Generate Text

Popular this week

In

Stackademic

by

Faisal haque

Want to Run Open-Source AI in Production? Start Here

Mehmet Özgen ÖZDOĞAN

Local AI Is Getting Stronger: Distributed Inference, Agent Concurrency, and the Projects Worth a…

In

AI Advances

by

Gavin Li

Can the New King of Open Source — Qwen3.8–27B — Really Run in 3GB of VRAM?

In

Google Cloud - Community

by

Karl Weinmeister

How to build a Jev-style classifier with DiffusionGemma and vLLM

In

Artificial Intelligence in Plain English

by

Faisal haque

How to Run Open-Source AI Models in Production: The Best Inference Servers

Latest stories

In

thecinderellaproject

by

Shalendra gaur

Your LLM agent re-reads its history every step. We measured what that costs

Varun Rajput

Why May a Model Get Slower on a Bigger Machine?

Mehmet Özgen ÖZDOĞAN

Local AI Is Getting Stronger: Distributed Inference, Agent Concurrency, and the Projects Worth a…

Priya Srivastava

AI Upskilling Day 1: How LLMs Actually Run : Tokens, Weights, and GPUs Explained

Lyndon Carlson

“Plan My Whole Year”: The Request That Made Us Build Our Own Model

See more stories

Who to follow

Popular this week

In

Stackademic

by

Faisal haque

Want to Run Open-Source AI in Production? Start Here

Mehmet Özgen ÖZDOĞAN

Local AI Is Getting Stronger: Distributed Inference, Agent Concurrency, and the Projects Worth a…

In

AI Advances

by

Gavin Li

Can the New King of Open Source — Qwen3.8–27B — Really Run in 3GB of VRAM?

In

Google Cloud - Community

by

Karl Weinmeister

How to build a Jev-style classifier with DiffusionGemma and vLLM

In

Artificial Intelligence in Plain English

by

Faisal haque

How to Run Open-Source AI Models in Production: The Best Inference Servers

Latest stories

In

thecinderellaproject

by

Shalendra gaur

Your LLM agent re-reads its history every step. We measured what that costs

Varun Rajput

Why May a Model Get Slower on a Bigger Machine?

Mehmet Özgen ÖZDOĞAN

Local AI Is Getting Stronger: Distributed Inference, Agent Concurrency, and the Projects Worth a…

Priya Srivastava

AI Upskilling Day 1: How LLMs Actually Run : Tokens, Weights, and GPUs Explained

Lyndon Carlson

“Plan My Whole Year”: The Request That Made Us Build Our Own Model

See more stories

Who to follow