Data Conference Databasea Query.Farm index
Speakers

Ron Kahn

Employers on the program

  1. 2026NVIDIA2 talks
Events2
Conferences2
Talks2
Years active2026

The year around now

Talks in the past 12 months and announced talks ahead, one row per conference, January to December. Hover a mark for the talk.

JanFebMarAprMayJunJulAugSepOctNovDecPyTorch ConferencePyTorch ConferenceAI EngineerAI Engineer (World's Fair, Summit and regional editions)
Held in the past 12 months Next 12 months Today, Nov 9, 2026

Appearances by year

201920202021202220232024202520262027
  • AI Engineer (World's Fair, Summit and regional editions)
  • PyTorch Conference

Talks

DateEventConferenceRoleTitleLinks
Sep 23, 2026AI Engineer Paris 2026AI Engineer (World's Fair, Summit and regional editions)workshopFrom Minutes to Seconds: Killing the Cold Start Tax on LLM Inference
as NVIDIA
Spinning up an LLM replica can be painfully slow. Before a fresh inference server instance outputs a single token, it has to move weights onto the GPU, spin up…Show less

Spinning up an LLM replica can be painfully slow. Before a fresh inference server instance outputs a single token, it has to move weights onto the GPU, spin up CUDA, sit through compilation, CUDA graph capture, engine initialization, and more. That's tens of minutes of idle GPU time, but that's the cheap part.

Apr 7, 2026PyTorch Conference Europe 2026PyTorch ConferencespeakerBeyond the Theory: What Actually Breaks When You Scale Your Disaggregated Pytorch Models
as NVIDIA
As inference demand explodes, new techniques to optimize these deployments have emerged. One such technique is disaggregated inference, which splits inference…Show less

As inference demand explodes, new techniques to optimize these deployments have emerged. One such technique is disaggregated inference, which splits inference into differently optimized workloads (e.g. prefill and decode) on separate workers. The theory is straightforward–better GPU utilization,...

Frequent co-speakers

SpeakerShared eventsShared talksLast together
Ben Burtenshaw2—2026
Dan Feigin112026
Ekin Karabulut112026

Speakers with the same name are merged into one entry, so this page may combine more than one person. Affiliations are shown as each conference listed them.