Reading

Building Large Language Models from Scratch: LLM-from-scratch Learning Practice

LLM-from-scratch is a learning and practice repository accompanying the book 'Building Large Language Models from Scratch'. By hands-on implementation of the Transformer architecture, attention mechanism, and training process, it helps developers gain an in-depth understanding of the internal working principles of large language models.

大语言模型Transformer注意力机制深度学习从零实现教育GPT自注意力

Published 2026-04-22 13:26Recent activity 2026-04-22 13:56Estimated read 1 min

Section 01

Building Large Language Models from Scratch: LLM-from-scratch Learning Practice

导读 / 主楼：Building Large Language Models from Scratch: LLM-from-scratch Learning Practice

Introduction / Main Post: Building Large Language Models from Scratch: LLM-from-scratch Learning Practice

Building Large Language Models from Scratch: LLM-from-scratch Learning Practice

导读 / 主楼：Building Large Language Models from Scratch: LLM-from-scratch Learning Practice

Introduction / Main Post: Building Large Language Models from Scratch: LLM-from-scratch Learning Practice

Continue Reading

Splinter: A Lock-Free Zero-Copy Shared Memory KV and Vector Storage Library That Eliminates Socket and Memcpy Overhead for LLM Inference

Folkering OS: When the Operating System Itself Is AI—A Self-Evolving Bare-Metal Rust System

LLM-assisted-analysis: A New Approach to Detecting Logical Vulnerabilities in Smart Contracts Using Large Language Models

LLM Inference Framework Performance Showdown: In-depth Evaluation of vLLM, SGLang, and Ollama on Ampere and Hopper Architectures