this post was submitted on 24 Mar 2026
4 points (100.0% liked)

Hacker News

4577 readers
436 users here now

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

founded 2 years ago
MODERATORS
patrick@lemmy.bestiver.se
rssbot@lemmy.bestiver.se
4
Pool spare GPU capacity to run LLMs at larger scale (github.com)
submitted 4 days ago by rssbot@lemmy.bestiver.se to c/hackernews@lemmy.bestiver.se
1 comments fedilink hide all child comments
 

Comments

you are viewing a single comment's thread
view the rest of the comments
[–] troed@fedia.io 1 points 4 days ago

That's really interesting. Only macOS instructions though? Seems like something that would easily run on Linux as well.

(I'd love to hook my server's GPU into local LLM workloads otherwise only offloaded to the CPU from my main workstation when needing too much VRAM)