from Hacker News

Talaria: Interactively Optimizing Machine Learning Models for Efficient Inferenc

by quantisan on 9/9/24, 11:29 PM with 6 comments

• by jgoertler on 9/10/24, 7:20 AM

  Hi, I’m Jochen, one of the authors.

  We recently did a Show HN (https://news.ycombinator.com/item?id=41463916) which did not get much traction, so I’m posting this again here:

  We just released Mycelium, the library that powers Talaria’s graph viewer. You can check it out and play around with it here: https://apple.github.io/ml-mycelium

  I’m happy to answer any questions about Talaria or Mycelium!

• by SaBaAg on 9/20/24, 9:11 PM

  Are inference metrics like latency and power measured live from device? To which devices can Talaria be applied?

• by efnx on 9/10/24, 10:25 AM

  How does this compare to TVM?

• by bobosha on 9/11/24, 1:58 PM

  Could you give us a tl;dr on this project? and how could I use something like this work for on-device applications, think "smart home" style applications?