decode

2 statements across 1 episodes · 1 bullish · 0 bearish · 1 people on the record · first statement Jul 29, 2026 by Misha Smulyanski · across every show →

Everything said about decode, oldest first

Jul 29, 2026 positive
Insight
Smulyanski: On-die SRAM accelerators excel at LLM decode due to high bandwidth
“The SRA machine basically keeps the entire weight matrix in SRA memory on DAI, so the, you got a lot more bandwidth, right, because it's on chip, right, so you can access, you know bytes over cycles, right, the chip interconnect is also fast, you can go, like …”
Misha Smulyanski Jul 29, 2026 ▶ 55:29 Multi-GPU Kernels, Intelligence per Watt, Heterogeneous Inference, and More | YC Paper Club · Y Combinator
Jul 29, 2026
Assertion Supported
Smulyanski: LLM decode workloads remain bandwidth-bound even across large batch sizes
“Pre-fill is generally very compute bound. Right because you basically do, ah, like, attention, ah, you do, ah, ah, a lot of, ah work for, you know, for, you know, all the tokens that you are fetching, right? You can, ah, you fetch the weights while I'm once an…”
Misha Smulyanski Jul 29, 2026 ▶ 51:45 Multi-GPU Kernels, Intelligence per Watt, Heterogeneous Inference, and More | YC Paper Club · Y Combinator
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 300 episodes 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.