this post was submitted on 13 Jun 2024
9 points (100.0% liked)

Hacker News

2171 readers
1 users here now

A mirror of Hacker News' best submissions.

founded 2 years ago
MODERATORS
bot@lemmy.smeargle.fans
9
AMD's MI300X Outperforms Nvidia's H100 for LLM Inference (www.blog.tensorwave.com)
submitted 1 year ago by bot@lemmy.smeargle.fans to c/hackernews@lemmy.smeargle.fans
2 comments fedilink hide all child comments
 

HN Discussion

you are viewing a single comment's thread
view the rest of the comments
[–] fubarx@lemmy.ml 5 points 1 year ago

Why are they only testing inference vs training?

Not many companies are going to want to deploy their own public-facing chatbot service. But almost everyone in this space is going to want to train their models, which is where the performance boost comes in.