Ani Katz: It’s an Enormous Privilege To Be Able To Make Art

In this interview, author Ani Katz discusses how an unforeseen personal experience founds its way into her new literary novel, Haven.

Speculative Speculative Decoding

Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upcoming tokens from a slower target model, and then verifying them in parallel with a single target model forward pass. However, speculative decoding itself relies on a sequential dependence between speculation and verification. We introduce speculative speculative decoding (SSD) to parallelize these operations. While a verification is ongoing, the draft model predicts likely verification outcomes and prepares speculations pre-emptively for them. If the actual verification outcome is then in the predicted set, a speculation can be returned immediately, eliminating drafting overhead entirely. We identify three key challenges presented by speculative speculative decoding, and suggest principled methods to solve each. The result is Saguaro, an optimized SSD algorithm. Our implementation is up to 2x faster than optimized speculative decoding baselines and up to 5x faster than autoregressive decoding with open source inference engines.

Foreverest – Scifi Short Story – Free Sample - Inkican

Foreverest is a scifi Short Story; This free sample - puts you into a world where billion-dollar dreams blur with deadly intentions. Get out while you can.

Is This Crypto’s Fimbulwinter?

Political power may not be enough to save the crypto cult

The Windspeaker