Very fast ALS on GPUs

[Wei Tan]

Hi Chris, I have been following your work on using MF to recommend music, great work!
We have an extremely fast ALS implementation on GPUs: https://github.com/wei-tan/CuMF/ . It is an order or magnitude faster than Spark ALS.

For now we do not support implicit-mf but it would be straightforward to add that. Maybe you find this interesting to you.
Thanks,
Wei

[Chris Johnson]

Nice! Thanks for sharing, I'll check it out.

On Mon, Sep 19, 2016 at 3:17 PM, Wei Tan [e-mail] wrote:

Hi Chris, I have been following your work on using MF to recommend music,
great work!
We have an extremely fast ALS implementation on GPUs:
https://github.com/wei-tan/CuMF/ . It is an order or magnitude faster
than Spark ALS.

For now we do not support implicit-mf but it would be straightforward to
add that. Maybe you find this interesting to you.
Thanks,
Wei

—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
#4, or mute the
thread
https://github.com/notifications/unsubscribe-auth/AA4qQtmDRmogAF2UZ9Q0389BXN2xJPLGks5qru3DgaJpZM4KA6rM
.

[Chris Johnson]

Closing since this isn't actually an issue.