RSSAmplifier

Blog

Reed Meyerson

reedmeyerson.comRSS feed ↗3 posts

Latest posts

Speculative Decoding Is Not a Heuristic

The Basic Idea Speculative decoding [1] , [2] is an inference technique for increasing the throughput of an LLM. In its most basic form, there is a large/slow target model and a small/fast draft model . The draft model is used to quickly generate a draft sequence of the next tokens 1 . Then, a single pass of the target model is used to obtain next-token distributions 2 . A verification procedure…

The Ancients had Ops

A Bit of History Pyramid building, tax collection, and war waging are not exactly simple enterprises. So complex are these operations, that their management requires a great technology. A technology so transformational, our modern Ops stacks pale in comparison. I speak, of course, of the technology of writing . Writing first appeared over 5,000 years ago in the ancient Mesopotamian civilization of…

Generative AI doesn’t need to be flashy

Generative AI is the new hotness. It’s flashy, exciting, full of pizazz. There’s a certain showmanship in asking a machine for an image of a monkey riding a unicycle and having it spit out an image of a monkey riding a unicycle. Most data scientists don’t deal with such exciting things. For most companies, pictures of monkeys riding unicycles have no effect on the bottom line; these flashy…