These days, large language models can handle increasingly complex tasks, writing complex code and engaging in sophisticated ...

High-performance matrix multiplication remains a cornerstone of numerical computing, underpinning a wide array of applications from scientific simulations to machine learning. Researchers continually ...

Abstract: In this paper, we propose three modular multiplication algorithms that use only the IEEE 754 binary floating-point operations. Several previous studies have used floating-point operations to ...

When you create an algorithm, you need to include precise, step-by-step instructions. This means you will need to break down the task or problem into smaller steps. We call this process decomposition.

As Transformer models continue to grow in size and complexity, numerous high-fidelity pruning methods have been proposed to mitigate the increasing parameter count. However, transforming these ...

CUDA-L2 is a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically optimize Half-precision General Matrix Multiply (HGEMM) CUDA kernels. CUDA-L2 ...