Friday, May 30, 2025

Start of archive·May 16

Top story

Platform WatchVercel Blog

Fluid compute: Evolving serverless for AI workloads

Traditional serverless infrastructure wasn't designed for LLM workloads' sustained compute and continuous execution demands. Vercel's 'fluid compute' signals a fundamental shift in how deployment platforms must architect for AI—a challenge every infrastructure vendor will face.

Traditional serverless designed for stateless, transactional web apps