Lemmy
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
RSS Bot@lemmy.bestiver.seMB to Hacker News@lemmy.bestiver.seEnglish · 1 day ago

Alibaba Cloud says it cut Nvidia AI GPU use by 82% with new pooling system

www.tomshardware.com

external-link
message-square
1
fedilink
  • cross-posted to:
  • [email protected]
  • [email protected]
2
external-link

Alibaba Cloud says it cut Nvidia AI GPU use by 82% with new pooling system

www.tomshardware.com

RSS Bot@lemmy.bestiver.seMB to Hacker News@lemmy.bestiver.seEnglish · 1 day ago
message-square
1
fedilink
  • cross-posted to:
  • [email protected]
  • [email protected]
Alibaba Cloud says it cut Nvidia AI GPU use by 82% with new pooling system— up to 9x increase in output lets 213 GPUs perform like 1,192
www.tomshardware.com
external-link
A paper presented at SOSP 2025 details how token-level scheduling helped one GPU serve multiple LLMs, reducing demand from 1,192 to 213 H20s.

Comments

  • 🇵🇸antifa_ceo@lemmy.ml
    link
    fedilink
    English
    arrow-up
    2
    ·
    1 day ago

    Uh oh my precious AI bubble!

Hacker News@lemmy.bestiver.se

hackernews@lemmy.bestiver.se

Subscribe from Remote Instance

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: [email protected]
lock
Community locked: only moderators can create posts. You can still comment on posts.

Posts from the RSS Feed of HackerNews.

The feed sometimes contains ads and posts that have been removed by the mod team at HN.

Visibility: Public
globe

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

  • 308 users / day
  • 1.66K users / week
  • 3.66K users / month
  • 9.52K users / 6 months
  • 1 local subscriber
  • 2.85K subscribers
  • 26.1K Posts
  • 13.1K Comments
  • Modlog
  • mods:
  • patrick@lemmy.bestiver.se
  • RSS Bot@lemmy.bestiver.se
  • BE: 0.19.9
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org