Booting Engineer Runtime ssh://sergiio@rhel-core-01
0% Click to skip · Esc to continue instantly
root@runtime:~#

Engineer Command Palette

Ctrl/Cmd + K
Skip to content
SB Sergio Barrientos Linux & Virtualization Engineer

Building enterprise infrastructure by day; deploying local AI and shipping Kotlin production apps by night.

Madrid · systems online CEST
01 Home ↗ 02 Field Notes Archive ↗ 03 About + CV ↗ 04 LLM Handbook ↗
in LinkedIn ↗ {} GitHub ↗ CV Curriculum Vitae ↓

sergio@field-notes:~$ _

Local AI / Systems Engineering

LLM Handbook

A complete engineering guide to understanding and deploying Large Language Models.

Transformer internals KV cache economics MoE + routing DeepSeek LSA
01
Fundamentals Chapter 1

LLM Handbook Part 1: Architecture, Attention Heads & Flash Attention

An engineer's guide to the core mechanics of Large Language Models. Demystifying the Transformer architecture, KV Cache, and how Flash Attention changed the game.

→
02
Advanced Architectures Chapter 2

LLM Handbook Part 2: Dissecting Modern Architectures (MoE, MTP, GLM)

Exploring the cutting-edge architectural quirks that power modern LLMs: Mixture of Experts (MoE), Multi-Token Prediction (MTP), and GLM's bidirectional attention.

→
03
Advanced Architectures Chapter 3

LLM Handbook Part 3: DeepSeek-V4, GQA & Lookahead Sparse Attention

How DeepSeek-V4 uses Grouped Query Attention and Neural Memory Indexers to achieve 500K context windows with a 90% VRAM reduction.

→
Sergio B. / Field Notes • Case-study driven engineering portfolio • As an Amazon Associate I earn from qualifying purchases.