Part 0 — Before you learn

Coding Ethics and Open-Source Spirit

Deploy Your First SGLang Server

Part I — Foundations

Chapter 1 Introduction to LLM

Chapter 2 Introduction to Inference

Chapter 3 Introduction to GPU

Chapter 4 KV Cache

Chapter 5 Introduction to Benchmark

Chapter 1 mini-sglang Overview

Chapter 2 Inside SGLang (Concepts)

Chapter 2 Inside SGLang (Code Walkthrough)

Chapter 3 Forward Pass and Generation

Chapter 4 KV Cache Optimization

Chapter 5 HTTP and Concurrent Requests (Concepts)

Chapter 5 HTTP and Concurrent Requests (Code Walkthrough)

Chapter 6 Continuous Batching and the Scheduler

Chapter 7 Paged KV Cache and Memory Management

Chapter 8 RadixAttention and Prefix Caching (Concepts)

Chapter 8 RadixAttention and Prefix Caching (Code Walkthrough)

Chapter 9 Multi-process and Tensor Parallelism

Chapter 10 Speculative Decoding

Chapter 1 Attention Backends and CUDA Graph

Chapter 2 Quantization and Low-Precision Inference

Chapter 3 Hierarchical Caching

Chapter 4 Scaling Out

Chapter 5 Prefill-Decode Disaggregation

Chapter 1 Deploying SGLang with the Cookbook

Chapter 2 Profiling and Trace Analysis

Chapter 3 SGLang PR Workflow

About

PR requirements

On this page

This chapter is being written. Stay tuned.

Pager