Join the engineers running inference at scale in production.
Learn from the engineers building the inference stack
Understand what actually works in production
Explore emerging inference architectures
Learn how teams are controlling costs at scale
The Three Pillars of Modern Inference
Engines
Inside today’s inference engines: schedulers, KV caches, serving systems, and the code powering them.
Mission Critical
Operating inference at scale: reliability, observability, and performance.
Economics
Building faster, cheaper, and more efficient inference platforms.
Let’s build the future of inference together.
Presented by