RSS Bot@lemmy.bestiver.seMB to Hacker News@lemmy.bestiver.seEnglish · 11 days ago

Alibaba Cloud claims to reduce Nvidia GPU use by 82%

1

6

Alibaba Cloud claims to reduce Nvidia GPU use by 82%

RSS Bot@lemmy.bestiver.seMB to Hacker News@lemmy.bestiver.seEnglish · 11 days ago

1

Alibaba Cloud claims to slash Nvidia GPU use by 82% with new pooling system

The new Aegaeon system can serve dozens of large language models using a fraction of the GPUs previously required, potentially reshaping AI workloads.

Chat

eleijeep@piefed.social
link
fedilink
English
arrow-up
1·
11 days ago
The paper, for anyone interested: https://ennanzhai.github.io/pub/sosp25-aegaeon.pdf

Hacker News@lemmy.bestiver.se

hackernews@lemmy.bestiver.se

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]

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

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

270 users / day
1.29K users / week
3.66K users / month
9.42K users / 6 months
1 local subscriber
2.9K subscribers
16.4K Posts
9.08K Comments
Modlog