Disaggregation

topic on 2 shows · 3 statements across 2 episodes

3 statements about Disaggregation, every show

Quantization, speculative decoding, and prefill-decode disaggregation each yield 2x speedups

“Going from BF-sixteen to NVFP four is, it's not quite a two X, right? It's like, I think it's about like 30, 30 to 40% from 16 to eight, and then another 30 to 40% multiplied from eight to four. So that doesn't quite get you a two X, but like roughly a two X. …”

Philip Kiely Aug 3, 2026 ▶ 40:03 Next 100x in AI: Inference, Networking, & Self-Optimizing Models — Philip Kiely & Ali Taha, Baseten

LATENT SPACE Prediction Not checkable as stated

NVIDIA Rubin will shift inference engineering toward traditional hardware infrastructure challenges

“I think that themes around like KV cache offloading, KV aware routing, and disaggregation are going to be substantially more important in the Rubin era, which means that inference engineering becomes not just a like CUDA kernel problem, but also like a very tr…”

Philip Kiely Aug 3, 2026 ▶ 1:01:52 Next 100x in AI: Inference, Networking, & Self-Optimizing Models — Philip Kiely & Ali Taha, Baseten

a16z Insight

Casado: Industry disaggregation typically expands total market size by 10x

“Every time you have a disaggregation, the market tends to grow by, say, a factor of 10.”

Martin Casado Mar 10, 2018 ▶ 7:31 The World Through an API

← every entity, every show

Turn any episode into a week of clips.

This entire site, thousands of episodes across every show transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

Disaggregation

3 statements about Disaggregation, every show

Turn any episode into a week of clips.