KP
Kevin Park
last week
The hand-drawn diagrams make abstract ideas click instantly. Wish every technical book was written like this.
Free preview available. Sign in and subscribe to unlock the full book.
Vizuara AI Labs · intermediate
LLM Production & Deployment
Take LLMs from notebook to production.
The full production stack for large language models: efficient serving with vLLM, text classification, clustering, prompt engineering, RAG, finetuning with LoRA and Unsloth, agents, and memory. Every stage is built hands-on the way real deployed systems are.
43 capsules161 figures~8 hoursby Dr. Raj Dandekar
Read on your Kindle or e-reader
Download the EPUB and read offline — perfect for the train. Works on Kindle, Kobo, Apple Books & more.
00Foundations of Language AI5 capsules
Foundations of Language AI — 5 chapters.
01Why Deploying LLMs Is Hardconceptfree10 min02The History of Language AIconceptfree11 min03Representation vs Generative Modelsconcept🔒11 min04Loading a Model with HuggingFacecode🔒11 min05Serving with vLLMcode🔒11 min01Efficient Inference at Scale4 capsules
Efficient Inference at Scale — 4 chapters.
06What Makes vLLM Efficientdeep-dive🔒12 min07Throughput: vLLM vs HuggingFaceproject🔒11 min08Quantization for Local Inferencecode🔒11 min09Choosing a BERT-Based Modelintuition🔒12 min02Text Classification with LLMs4 capsules
Text Classification with LLMs — 4 chapters.
10Classification with Representation Modelsconcept🔒12 min11Decoder & Encoder-Decoder Classificationconcept🔒12 min12Building a Text Classifiercode🔒9 min13Zero-Shot vs Finetuned Classificationintuition🔒13 min03Clustering & Topic Modeling4 capsules
Clustering & Topic Modeling — 4 chapters.
14Text Clustering with Language AIconcept🔒11 min15Topic Modeling with Language AIconcept🔒10 min16Clustering & Topic Modeling Hands-Oncode🔒13 min17Project: Customer Support Clusteringproject🔒12 min04Prompt Engineering in Production5 capsules
Prompt Engineering in Production — 5 chapters.
18Controlling Model Outputconcept🔒10 min19Basic Prompt Engineeringintuition🔒13 min20Advanced Prompting: CoT & ToTdeep-dive🔒11 min21Self-Consistency & Multiple Reasoning Pathscode🔒10 min22Evaluating Prompt Effectivenessproject🔒12 min05RAG in Production6 capsules
RAG in Production — 6 chapters.
23The RAG Production Workflowconcept🔒12 min24Data Ingestion & Chunkingcode🔒12 min25Chunking Strategies Compareddeep-dive🔒13 min26Embedding & Retrievalcode🔒12 min27Generation & Groundingconcept🔒13 min28Building a RAG Web Appproject🔒12 min06Finetuning LLMs8 capsules
Finetuning LLMs — 8 chapters.
29The Basics of LLM Finetuningconcept🔒14 min30Finetuning GPT-2 from Scratchcode🔒11 min31Tokenization & Padding for Finetuningcode🔒12 min32Finetuning with HuggingFace & Unslothcode🔒12 min33LoRA & Parameter-Efficient Finetuningmath🔒11 min34Soft-Prompt & Prefix Tuningcode🔒13 min35Full vs LoRA Finetuning a Classifierproject🔒13 min36Finetuning Research: Subliminal Learning & RAFTdeep-dive🔒13 min07Agents & Memory7 capsules
Agents & Memory — 7 chapters.
37Agents & the TAO Loopconcept🔒10 min38Building a Multi-Agent Frameworkcode🔒13 min39Orchestrating Agents with LangGraphcode🔒12 min40Agentic RAGdeep-dive🔒13 min41Project: Agents in Industryproject🔒14 min42Memory in LLM Systemsconcept🔒10 min43Project: Personalized Tutor with Mem0project🔒11 minRatings & reviews
1,797 readersRate this book
AM
Aarav Mehta
4 months ago
Practical and rigorous at the same time. I went straight from reading a capsule to shipping it at work.
MB
Marcus Bell
4 months ago
A few sections moved fast for me, but re-reading with the figures open made everything land. Highly recommend.
NK
Noah Kim
6 months ago
This is the resource I wish I had when I started. Clear mental models, zero fluff.