All the Things We Have to Do to Satisfy Your Insatiable Need for Tokens
Official Schedule Context
- Date/time: 2026-07-01 · 11:40am-12:00pm
- Track/room: Inference · Leadership 1
- Speaker(s): Daniel Kim, Michelle Nguyen
- Session type/status: session · confirmed
Official Description
Every time the industry figures out how to serve tokens faster and cheaper, the appetite grows to
match. Models get bigger, contexts get longer, agents start chaining thousands of calls together.
The finish line keeps moving. This talk is a technical tour through everything the industry has done
to keep up, led by two experts in high-performance inference. We'll start with the optimizations
that made hardware work harder without changing the underlying architecture. Then we'll go up a
level with techniques that work smarter across requests and across the model itself. And finally, a
peek into the future with heterogeneous disaggregated inference, the architectural shift that splits
prefill and decode across specialized hardware, and even more advanced forms of hardware
specialization coming your way soon. Token demand is about to get a lot more insatiable. Let's see
what the future has in store for us!
Related YouTube Video
From Mixture of Experts to Mixture of Agents with Super Fast Inference - Daniel Kim & Daria Soboleva (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).
Transcript Status
Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.
People
Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.
Supporting Slides
- youtube tzRvcTEapzo slides — extracted from the related public AI Engineer video.
Slide Evidence
- Slide-only cropped deck: youtube tzRvcTEapzo dense slides (5 viable slide images).
- Related slide/OCR pages:
- youtube tzRvcTEapzo dense slides
- youtube tzRvcTEapzo reconstructed slides
- youtube tzRvcTEapzo slides
- Slide-derived terms:
microsoft,mixture,models,research,experts,daniel,daria,approach,queen,head,engineering,memory,conte,awws,graphite,windsurf,mongobb,mdaily