Your GPU is not compute-bound. It is memory-bound. The KV cache is eating half your inference budget, and two ICLR 2026 breakthroughs KVTC and TurboQuant are about to change the math entirely.
Podzilla Summary coming soon
Sign up to get notified when the full AI-powered summary is ready.
Free forever for up to 3 podcasts. No credit card required.
Listen to This Episode
More from The Practical AI Digest
Retrieval-Augmented Generation Is Broken: How to Fix It
Distillation: How Small Models Eat Big Models for Lunch
World Models: When AI Learns Physics Instead of Memorizing Data
The Evaluation Crisis: We Do Not Know How Good Our Models Actually Are
Get summaries like this every morning.
Free AI-powered recaps of The Practical AI Digest and your other favorite podcasts, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.