Code with me: Machine learning on a Macbook GPU (works for all M1, M2, M3) for a 10x speedup

preview_player
Показать описание
Step aside, NVIDIA CUDA! Apple Macbooks now have powerful M1 M2 M3 chips that are great for machine learning. This is your complete guide on how to run Pytorch ML models on your Mac’s GPU, instead of the CPU or CUDA. A machine learning engineer walks you through the easy, simple code changes needed to tap into your GPU - with only 5 lines of code! As a result, you’ll see a 10-20x speedup when running or training your ML models 🚀

TIMESTAMPS
00:00 Hello nerd :3
01:24 Train Predict Checkpoint
06:07 Compiling Data types
09:27 On Device
11:24 Subscribe boo

Connect with me ✨

#apple #machinelearning #gpu

SOURCES
Apple product video materials by Apple Inc
Background music
Creative Commons — Attribution-NoDerivs 3.0 Unported — CC BY-ND 3.0

Disclaimer:
This video contains clips from Apple Inc events, which are used and modified under fair use for educational/critical/commentary purposes. I do not claim ownership of the original materials used in this video. This content is not affiliated with, endorsed, sponsored, or specifically approved by Apple Inc and Apple Inc is not responsible for it. For more information about Apple’s original content, please visit their official website.
Рекомендации по теме
Комментарии
Автор

I've been looking for something like this for MONTHS! It's not so clear how to go from CUDA to mac. Thank you for compiling all into one place

vanessaaa.paaark
Автор

I just noticed in your terminal “Tams beast mac” 😂👌

tiffany
Автор

Finally! Now I don't need to buy a separate NVIDIA GPU rig

cryptamie
Автор

Thanks.... Playing around with an LLM on my mac.. and got your video as recommendation. Appreciated 👍

qbs
Автор

Auntie has arrived 🎉🎉🎉🎉🎉🎉🎉🎉🎉 booyakah booyakah bop bop bop burn fyah 🔥 dun know yes eye (Jamaican 🇯🇲 voice)

Hierothewordsmith
Автор

When me and my AI bots finally take over the world. I’ll refer back to this video and all your others.

estyalasu
Автор

Wow she is adorable. My Cuda GPU is throbbing right now. Great video and great info.

Mbro-dqdo
Автор

Subscribed and looking forward to future videos!

In the future, can you increase the font size or zoom in on the code you’re viewing/editing to make reading it easier on screen for those of us using an iPad or another small screen?

JoeBurnett
Автор

great video and happy to subscribe. was listening to this on my dog walk and now will watch it. one advice regarding videos for people listening only, lots of "this" and "that".

mistercakes
Автор

If you use Pytroch Lightning, it will assign your device for you automatically and it supports mps

Khari
Автор

Very good, but now try to directly compare the same model training between a monster notebook with an Nvidia GPU and a MacBook. That would be great. Which one wins? What's the performance difference?
Thanks for the great video.

peryclesjunior
Автор

Excellent video and topic - but how do M1 chips compare to an nvidia gpu in terms of performance? - Also, would love to see videos on Pytorch and deep learning with time series data...

themarksmith
Автор

Any suggestion on the number of gpu cores we need to run these models? TIA 😊

sanjana
Автор

I didn't know that pytorch added shaders for computing on apple silicon. I noticed that for torch geometric they do not have apple shaders, but they do have cuda

skanderbegvictor