0 views
Why is scheduling AI requests so difficult and expensive? 💸 Chris Wright and Carlos Costa explore why standard Kubernetes isn’t enough for AI inference, explaining the unique "shape" of AI requests and how a smarter scheduler can prevent costly over-provisioning. Learn how to build a smarter AI platform in the full Technically Speaking episode!
#AIInfrastructure #Kubernetes #LLM #AIEngineering #llmd #RedHat
Date: August 29, 2025
