Skip to content
GPU Support

3 years ago

With our new runtime, it's now possible to do GPUs

This thread is to guage interest. Please upvote it and we will keep you updated

40 Replies

3 years ago

GPUs would go so hard 🔥🔥🔥


3 years ago

Very much possible

https://x.com/justjake/status/1772005308052943005?s=46&t=00dq48d1c_GjD9m8fXEJ8w

However, GPUs have a liquidity problem (expensive for us to just keep em idle)

So, if you're interested, please upvote and once we hit enough demand, we can look into rolling this out broadly


3 years ago

We need this!


imw

2 years ago

+1!


xander

2 years ago

would be able to try this out


admin-replies

2 years ago

+1


ve-jo

2 years ago

+1


2 years ago

+1


sts417

2 years ago

+1


tony-hunter

2 years ago

+1


brentably

2 years ago

+1


2 years ago

+1


marcellov7

2 years ago

+1


2 years ago

Yesss +1


dzusooo

2 years ago

+1


inngeniero

2 years ago

+1


marcellov7

2 years ago

there are news on this?

to use Ollama on Railway, it would be a perfect combo!


viktorlarsson

2 years ago

I would really need this


thiagoscodelerae

2 years ago

+1


paddasecurity

2 years ago

+1


hypnobrew

2 years ago

+1000


iliefski

2 years ago

Hoping to move some GPU heavy services to railway ASAP.

+1


joshuanitschke

a year ago

+1


jonahseguin

a year ago

+1 need GPUs


scbeacham

a year ago

I currently use railway (just on hobby plan at the moment but definitely would upgrade), but am now building AI Image Generation applications with need for GPU. Would definitely prefer to stick with railway as, of all the deployment platforms I've tried, you guys are the most streamlined and easy to use.

Do we have any update on GPU services becoming available on railway? is there enough interest/resources to make it worth it yet for you to "flip that switch"? (I'm aware the implementation is significantly harder than that, you guys just make everything look so easy, thank you for that by the way!)


geo-ops

a year ago

+1


davidcoleman007

a year ago

I also would use this. understand the liquidity issues. I am looking to use high fidelity image upscaling. i wonder if there's a secure shared model that could allow us to not need per-user dedicated instances? This can allow us to scale as needed, without incuring massive idle costs for you.


59023g

9 months ago

Updates here?


jailsonpaca

9 months ago

+1


ptav

9 months ago

We're building an AI tool that uses a combination of local and public LLMs. CPU only workflow is very slow for some use cases so will need to purchase GPU capability in the next 2-4 months. Would greatly prefer to stay within Railway if possible


douglas125

8 months ago

I would have use cases for GPUs as well. My scale would not occupy it too much though


ninomandelab

7 months ago

Any updates here? Would also be interessted in the option to have GPUs


bananacy

7 months ago

I'm building a photo stock marketplace could really use gpu to crunch the images


saksham-dealstudio

6 months ago

We need this!


topprojectscreator

5 months ago

+1


Anonymous

4 months ago

+1


Anonymous

3 months ago

+1


2 months ago

+1


2 months ago

+1


milocoombs2002

a month ago

Very keen for this. What is the status for this?


Welcome!

Sign in to your Railway account to join the conversation.

Loading...