Tag
A cheatsheet covering memory segmentation concepts, likely useful for students and developers.
Published a GitHub repository with an LLM learning path for beginners, covering course content from Transformer basics to LLM techniques, with one course updated daily.
CMU Advanced NLP course by Wellecks now has all 23 lectures on YouTube with public slides and 20 code examples, covering LLM fundamentals and recent research.
This paper provides a 211-page collection of pen-and-paper exercises covering key topics in machine learning, including linear algebra, optimisation, graphical models, and variational inference, intended as an educational resource.
Dogesh is a Python-based interpreted programming language where every keyword is inspired by dog sounds, designed as a fun and educational compiler/interpreter project.
An introduction to a learning track on building load balancers from scratch, covering algorithms like round robin, least connections, consistent hashing, and practical pitfalls such as health check intervals.
Promotes an educational resource explaining Transformer architecture, covering token embeddings, self-attention, residual connections, and connections to GPT and BERT.
A Twitter thread about system design that promises to improve skills by the end of 2026.
This paper by Brandon Sandhu provides a mathematically rigorous yet accessible derivation of the Transformer architecture, covering tokenization, embeddings, attention mechanisms, and other core components, with prerequisites in linear algebra, calculus, probability, and information theory.
An interactive educational article that explains the functionality of internal combustion engines, starting from simple cranks and pistons to detailed animations of four-stroke cycles.
A detailed technical article explaining drone physics, including coordinate systems, equations of motion, forces, and control, with references to the multirotor simulation framework.
Introduces a free small book "Virtual Memory From First Principles", focusing on explaining virtual memory principles.
Recommends the open-source ebook project 'Claude Code From Scratch', which reproduces the core architecture of Claude Code with approximately 4300 lines of code, helping to understand how coding agents work.
Project Box is a collection of projects designed for C beginners, containing 10 projects of varying difficulty, from Tic-Tac-Toe to network programming. Each project includes source code, documentation, and build configurations, helping learners master C through practice.
NanoEuler is a GPT-2-scale language model built entirely from scratch in C/CUDA without any ML libraries, including hand-written forward/backward passes, a byte-level BPE tokenizer, and training pipeline. The project is an educational artifact demonstrating the engineering behind transformer training and runs on a single RTX 4070.
Tau is an educational Python coding agent that teaches you how to build agent harnesses, with transparent architecture and tutorials.
An interactive web page that visualizes a tiny transformer with editable weights, allowing users to see how changes affect predictions in real time, aimed at helping developers understand the forward pass of an LLM.
Updated 2204-page PDF mathematics ebook covering algebra, topology, differential calculus, and optimization theory for computer science and machine learning, released by Jean Gallier and Jocelyn Quaintance.
The UC San Diego Hao AI Lab blog provides a clear explanation of DistServe's Prefill Decode Disaggregation, tracing its acceptance from 2024 to 2025 and linking to related technologies like NVIDIA Dynamo, llm-d, Ray Serve LLM, LMCache, and MoonCake, making it a great starting point for learning LLM inference.
A tweet promoting TensorTonic, a platform that allows users to practice implementing nine common activation functions (Sigmoid, ReLU, Tanh, Softmax, Leaky ReLU, GELU, Swish, ELU, SELU) from scratch, including forward pass and gradient computation.