join us next week to learn about speculative decoding!
Hugging Face announces a livestream on speculative decoding for local LLMs
AISummary
Hugging Face says a livestream next week will explain speculative decoding, a method for speeding up local LLMs with multipliers. The speakers are Merve Noyan, Maarten Grootendorst, and Eldar Kurtic.
Post on XView on X
merveVerified on X
@mervenoyann
Learn about how to get multipliers in local LLM speed-ups using speculative decoding in this livestream with @mervenoyann, @MaartenGr and @_EldarKurtic https://www.youtube.com/watch?v=H4azmWcqO5g
Source: merve · x.comPublished · added here