MDHome · 38 topics · 312 subtopics

LLM Learning Hub

An IDE-style learning environment for Large Language Models. From Python foundations to inference optimization — explore 38 topics with concise explanations, code examples, and references.

Your progress

Select a topic below to begin or continue learning.

All Topics

Each topic contains multiple subtopics with concise explanations and code examples. Click any card to open its detail page.

017 files

Computer & Python Foundations

Python · GPU & VRAM

0211 files

Mathematics

Scalars · Gradient Descent

038 files

Machine Learning

Machine Learning · Generalization

0412 files

Neural Networks

Perceptron · Epoch

057 files

NLP

Text Representation · GRU

0612 files

Tokenization

Tokenization · Token Count

077 files

Embeddings

Token Embeddings · Semantic Search

086 files

Positional Information

Token Position · RoPE

0912 files

Attention

Attention · Attention Mask

106 files

Multi-Head Attention

Attention Head · Output Projection

1110 files

Transformer

Transformer Architecture · GPT Architecture

126 files

Language Modeling

Language Model · Causal Language Modeling

137 files

Text Generation

Greedy Decoding · Beam Search

146 files

Stopping Generation

EOS Token · Generation Loop

159 files

LLM Architecture

Model Parameters · Number of Heads

166 files

Context Window

Context Window · Context Limit

1715 files

LLM Training

Pretraining · Validation

1810 files

Build a Small LLM

Book Dataset · Model Inspection

195 files

Model Precision

Floating-Point Numbers · Mixed Precision

2014 files

Quantization

Quantization · Quantized Inference

217 files

GPU & Memory

VRAM · KV Cache Memory

225 files

KV Cache

Key Cache · Prefix Caching

236 files

Fine-Tuning

Fine-Tuning · PEFT

247 files

LoRA

Low-Rank Adaptation · QLoRA

256 files

Alignment

Human Preferences · DPO

2612 files

RAG

Retrieval-Augmented Generation · Grounded Generation

2710 files

Vector Search

Vector Database · Reranking

287 files

Function Calling

Tools · Tool Calling Loop

298 files

Agents

AI Agents · Multi-Step Tasks

309 files

Inference

LLM Inference · Streaming

314 files

Inference Optimization

Flash Attention · Compute Optimization

327 files

Distributed Training

Distributed Computing · Communication Overhead

336 files

Mixture of Experts

Mixture of Experts · Load Balancing

347 files

Multimodal LLMs

Multimodal Models · Cross-Modal Representation

356 files

Reasoning Models

Reasoning · Reward Signals

3610 files

Evaluation

Model Evaluation · Throughput Evaluation

379 files

LLM Systems

Model Serving · Cost Optimization

3810 files

LLM Research

Research Papers · Inference Experiments