Google's TurboQuant compresses AI memory by 6x, rattles chip stocks

thenextweb.com

cross-posted to:
technology@beehaw.org

Google's TurboQuant compresses AI memory by 6x, rattles chip stocks

thenextweb.com

sabreW4K3@lazysoci.al to

Tech@programming.devEnglish · 7 months ago

cross-posted to:
technology@beehaw.org

Google's TurboQuant algorithm compresses LLM key-value caches to 3 bits with no accuracy loss. Memory stocks fell within hours of the announcement.

You must log in or register to comment.

Chat

Tech@programming.dev

tech@programming.dev

Create a post

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !tech@programming.dev

A community for high quality news and discussion around technological advancements and changes

Things that fit:

New tech releases
Major tech changes
Major milestones for tech
Major tech news such as data breaches, discontinuation

Things that don’t fit

Minor app updates
Government legislation
Company news
Opinion pieces

Community Wiki

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

1 user / day
1 user / week
204 users / month
391 users / 6 months
9 local subscribers
3.46K subscribers
212 Posts
1.45K Comments
Modlog

mods:
Vacant@programming.dev