DeepSeek open-sources inference optimizations with 60–85% faster generation [pdf]

github.com

DeepSeek open-sources inference optimizations with 60–85% faster generation [pdf]

github.com

RSS Bot@lemmy.bestiver.seBM to Hacker News@lemmy.bestiver.seEnglish · 4 months ago

DeepSpec/DSpark_paper.pdf at main · deepseek-ai/DeepSpec

github.com

DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms - deepseek-ai/DeepSpec

Comments

You must log in or # 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: [email protected]

Community locked: only moderators can create posts. You can still comment on posts.

NOTICE: The bot occasionally has downtime, sorry about that. I’m working on adding better monitoring and error recovery so I can get notified faster.

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.

605 users / day
1.84K users / week
3.78K users / month
8.17K users / 6 months
3 local subscribers
5.7K subscribers
48.5K Posts
29.6K Comments
Modlog