Principles

Tokenization Basics BPE Algorithm GPT Tokenizers BPE Training Engineering

Model Architecture

From token ids to logits Embedding and LM Head

Attention Mechanisms

From Self-Attention to GQA Attention Sink

Position Encoding

Position Encoding Basics RoPE Math Derivation RoPE Implementation Length Extrapolation

GPU Programming Basics

GPU Architecture Basics Tensor Layout Triton Basics: Vector Add

Flash Attention Principles From Naive to Auto-Tuning Block Pointers and Multi-Dim Support Causal Masking Optimization Grouped Query Attention Backward Pass

Distributed Training

Data Parallelism ZeRO Optimizer Fully Sharded Data Parallel 张量并行流水线并行多维混合并行

Hands-on Training

Pretraining Data Tokenizer Training Model Architecture Data Pipeline Training Loop Monitoring and Validation

FundamentalsModel Architecture

Rotary Position Embedding

Premium

From position encoding basics to RoPE math, implementation, and length extrapolation

Log in to continue reading

This is premium content. Please log in to access the full article.

Attention Sink

Why the first token absorbs most attention, and the mechanism, cost, and removal paths of this phenomenon

Position Encoding Basics

Why Transformers need position information, and the methods and limits of absolute position encoding

Table of Contents