Search Results for "teaching"

how-to-optim-algorithm-in-cuda is an open educational repository focused on teaching developers how to optimize algorithms for high-performance execution on GPUs using CUDA. The project combines technical notes, code examples, and practical experiments that demonstrate how common computational kernels can be optimized to improve speed and memory efficiency. Instead of presenting only theoretical explanations, the repository includes hand-written CUDA implementations of fundamental operations such as reductions, element-wise computations, softmax, and attention mechanisms. ...

...The project also highlights best practices for working with LLMs, including prompt design and optimization strategies. By focusing on clarity and depth, it serves as both a teaching tool and a reference for developers. Overall, dive-into-llms provides a structured and practical approach to mastering modern language model technology.

Generative AI with JavaScript is an educational repository created by Microsoft that teaches developers how to build applications powered by large language models using the JavaScript ecosystem. The project is structured as a multi-lesson curriculum that introduces the concepts, tools, and practical techniques required to create generative AI applications. Each lesson includes written explanations, hands-on exercises, quizzes, and supporting videos to help developers learn the material...

ReCall is an open-source framework designed to train and evaluate language models that can reason through complex problems by interacting with external tools. The project builds on earlier work focused on teaching models how to search for information during reasoning tasks and extends that idea to a broader system where models can call a variety of external tools such as APIs, databases, or computation engines. Instead of relying purely on static knowledge stored inside the model, ReCall allows the language model to dynamically decide when it should retrieve information or invoke external capabilities during the reasoning process. ...

...The architecture mirrors the structure of the LLaMA-2 model family, allowing compatible model checkpoints to be converted and executed within the simplified runtime environment. Because the implementation is intentionally minimal, it serves as a teaching tool for understanding how transformer architectures operate at a low level.