Cutting inference cold starts by 40x with LP, FUSE, C/R, and CUDA-checkpoint

modal.com

Cutting inference cold starts by 40x with LP, FUSE, C/R, and CUDA-checkpoint

modal.com

RSS Bot@lemmy.bestiver.seMB to Hacker News@lemmy.bestiver.seEnglish · 12 days ago

Cutting inference cold starts by 40x with LP, FUSE, C/R, and cuda-checkpoint

modal.com

A deep dive on Modal's deep tech for fast boots.

Comments

You must log in or register to comment.

Chat

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: !hackernews@lemmy.bestiver.se

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.

Source of the RSS Bot

Visibility: Public

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

346 users / day
1.65K users / week
2.74K users / month
2.75K users / 6 months
12 local subscribers
4.93K subscribers
15.5K Posts
7.66K Comments
Modlog