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

Attention Mechanisms

Premium

From MHA / Causal / GQA to Attention Sink and Gated Attention, understand the design, flaws, and evolution of attention

Log in to continue reading

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

Embedding and LM Head

Understand how token ids enter a continuous vector space, and how hidden states are projected back to vocabulary logits

From Self-Attention to GQA

Starting from Self-Attention, unpack the design trade-offs of Multi-Head, Causal Masking, and GQA / MQA in turn

Table of Contents