Tag
A free, open-source structured digital notebook called 'Before GPU Engineering' with 56 chapters that teaches GPU architecture and performance engineering from the ground up, covering warps, SIMT, memory hierarchies, kernel optimization, and profiling for AI/ML engineers.
The GitHub repository cs329z-chinese organizes the publicly available materials from Stanford’s CS329Z “Engineering AI Agents” course into a Chinese-language self-study tutorial, featuring 19 lectures, 4 hands-on exercises, and a web version that can be read offline. It is designed to help developers who know Python systematically learn agent development.
A user shared a helpful guide on LLM inference by @lamhot_ai that covers the high-level details of inference, and added annotations highlighting the most important parts.
An introduction to the claude-howto tutorial repo on GitHub, which helps users get started from zero with Claude Code's advanced features — subagents, hooks, skills, and MCP servers — through 10 modules, visual Mermaid diagrams, and ready-to-use templates.
An open-source LLM engineer's practical handbook called time-to-first-token, offering a 10-week, 50-lesson roadmap to build a production-ready, OpenAI-compatible inference service from scratch — covering vLLM source code, PagedAttention, monitoring, 1000+ concurrency load testing, and quantization optimization.
Discover AI 是一款离线学习应用,提供 51 个动手实验,从神经元、梯度下降到注意力、RAG、智能体、微调、量化与部署,部分实验可真实运行(如内置 1.37M 参数的小型 transformer),无需账号且无遥测,代码已在 GitHub 开源。
A GitHub repository providing a complete Chinese Markdown version of 'Computer Systems: A Programmer's Perspective' with exercises, answers, and lab instructions, along with an online reading website.
A tweet recommends CS336 as a starting point for learning about LLMs, architectures, and kernels.
An open-source, free online English grammar project designed to systematically build a solid foundation in English grammar through graded difficulty levels, supporting self-study and classroom use.
A tweet from @real_deep_ml recommending a machine learning book and highlighting the Deep-ML platform's approach to teaching core concepts with NumPy and projects with scikit-learn or PyTorch.
A GitHub repository providing a structured 100-day learning plan for LLM inference engineering, covering topics from CUDA kernels to autoscaling, with runnable scripts.
GitHub_Daily recommends an open-source project called ai-agents-from-scratch. It starts from zero and uses local models to gradually implement core patterns such as tool calling, memory, and ReAct loops, helping developers understand the underlying principles of AI Agents without directly using frameworks.
FreeCodeCamp published a full book teaching how to build a production-ready DevSecOps platform from homelab to AWS, covering Kubernetes, CI/CD, GitOps, security scanning, and observability.
Zig by Example is a hands-on introduction to the Zig programming language, featuring annotated example programs for version 0.16.
The tweet shares a compressed video version of the essence of the Google and Kaggle joint AI Agent 5-day special course, removing fluff and repetitive content, retaining core dry goods.
Recommends an open-source Chinese AI Agent general knowledge tutorial website, including 21 chapters with visualized animated tutorials, a 130+ question bank, and an AI teaching assistant. It is purely static and can be deployed to Nginx with one click.
Recommend 'The Little Book of Reinforcement Learning' as an introductory textbook for reinforcement learning. It's short but covers fundamentals to algorithms, and comes with PyTorch implementations and supplementary derivations, suitable for understanding core RL concepts.
A tweet promoting a GitHub repository containing over 300 real ML system design case studies from major companies like Google, Amazon, Microsoft, and Netflix, aiming to teach how production ML systems are actually built.
Kyle Kingsbury shares a free outline for a 16-32 hour distributed systems fundamentals class, covering theory, algorithms, and practical production concerns, with optional labwork via Maelstrom.
A set of four cards covering the core concepts of neural networks: neuron, forward pass, activations, and backpropagation, aimed at helping learners understand how models from perceptrons to transformers work.