StarZero All shows Try the podcast clipper →

speculative decoding

1 statements across 1 episodes · 1 bullish · 0 bearish · 1 people on the record · first statement Jan 22, 2026 by Dan Fu · across every show →

Everything said about speculative decoding, oldest first

Jan 22, 2026 positive
Insight
Dan Fu: Proper speculative decoding yields 2x to 3x model speedups
“So if you do the speculative decoding right, you can get, again, two X, three X speed ups over, over, you know, just running a vanilla model.”
Dan Fu Jan 22, 2026 ▶ 57:34 The End of GPU Scaling? Compute & The Agent Era — Tim Dettmers (Ai2) & Dan Fu (Together AI)
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 400 conversations 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.

Try the podcast clipper Learn more