Blogs

AI CUDA Engineer: Automating CUDA Kernel Optimization with LLMs

20-02-2025

Sakana AI's AI CUDA Engineer automates CUDA kernel optimization using LLMs, achieving up to 145x speedup over PyTorch. Learn how it works and its potential impact on high-performance computing.

Making API Calls with DeepSeek vs. OpenAI: Key Differences

04-02-2025

Learn how to make DeepSeek API calls in your JavaScript application using the openai npm package in this step-by-step guide.