scripod.com
1,000 tokens per second: the case against predicting one word at a time (Kumar, VP of Engineering at Inception)

Highlights

Transcript

Chapters

Pins

1,000 tokens per second: the case against predicting one word at a time (Kumar, VP of Engineering at Inception)

The Infra Pod
OverviewShownote
Unprocessed episode, you can be the first!

Shownote

What if the entire LLM industry has been solving language generation the slow way — one token at a time? In this episode of The Infra Pod, hosts Tim Chen (GP at Essence VC) and Ian Livingstone (CEO of Keycard) sit down with Kumar, VP of Engineering at ...

Highlights

Chapters

Transcript