The Inference Optimization Meetup

​The Inference Optimization Meetup

​We bring together entrepreneurs, industry professionals, engineers, and researchers for technical conversations on what it takes to run AI at scale, from inference and model serving to systems, optimization, and performance.

​🗓 Agenda

​6:00 – 6:55 PM – Food, Drinks & Community Mixer

​6:55 – 7:00 PM – Opening Remarks

​7:00 – 8:20 PM – Talks

• ​Ziv Bakhajian - Head of Research @ Impala AI – "Getting More Out of Speculative Decoding"

• ​Omer Shlomovits - CEO @ MoonMath.ai – "Principles of High-Performance Inference Serving"

• ​Roy Shchory - Senior Director of R&D @ Crusoe – "Large-scale production inference. Case studies & bottlenecks from serving frontier models at scale."

• ​Dan Shamesh - Software Development Engineer @ Decart – "Bottom Up Optimizatioמ on Nvidia Blackwell GPUs"