Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
An open-source that takes an AI model as input and outputs a much faster version (github.com/nebuly-ai)
3 points by zzz_sleeping on April 11, 2022 | hide | past | favorite | 1 comment


There's this new cool library on github for AI inference optimization.

https://github.com/nebuly-ai/nebullvm

As for the github readme, nebullvm is an open-source library takes your AI model as input and outputs an optimized version that runs 5-20 times faster on your machine. Nebullvm tests multiple deep learning compilers to identify the best possible way to execute your model on your specific hardware, without impacting the accuracy of your model.

The goal of nebullvm is to let any developer benefit from deep learning (DL) compilers without having to spend tons of hours understanding, installing, testing and debugging this powerful technology.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: