ylai@lemmy.ml to

LocalLLaMA@sh.itjust.worksEnglish · 1 year ago

Mozilla's Llamafile 0.8.2 Scores Big With New AVX2 Performance Optimizations

www.phoronix.com

3

1

Mozilla's Llamafile 0.8.2 Scores Big With New AVX2 Performance Optimizations

www.phoronix.com

ylai@lemmy.ml to

LocalLLaMA@sh.itjust.worksEnglish · 1 year ago

3

Chat

xcjs@programming.dev
link
fedilink
English
arrow-up
1·
edit-2
10 months ago
I just wanted to update this to mention that there are a lot of custom low level performance improvements for CPU based inferencing in Llamafile: https://justine.lol/matmul/

LocalLLaMA@sh.itjust.works

localllama@sh.itjust.works

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]

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

Visibility: Public

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

27 users / day
92 users / week
501 users / month
884 users / 6 months
1 local subscriber
2.96K subscribers
164 Posts
529 Comments
Modlog