
The Chips Got Faster. The Stack Didn't.
The bottleneck has moved.
Blog
Runpod continues to add to its fleet and add new data centers to bolster supply offerings.
.jpeg)
We've definitely heard the concerns about how difficult it can be to get the specific GPU spec that you want on Runpod, and we've been hard at work securing new supply to make this easier. We want your development efforts to succeed, and this won't happen if we can't provide the hardware.
Towards this goal, we've added a data center in AP-IN-1 with over 1MW of power capacity, which will focus on providing H100 80GB HBM3s.
Additional regions are already in various stages of buildout, and we'll keep shipping these announcements as sites come online. The short version of our commitment: if the GPU you want is one people are actually asking for, our job is to make sure you can get it on Runpod.
If there's a specific GPU SKU or region you'd like to see prioritized, reach out through our Discord or support, or drop a note to our sales team. The feedback genuinely shapes what we build next.
AP-IN-1 is live in the Runpod console right now.

To deploy:
Thanks, as always, for building on Runpod, and keep the feedback coming, no matter what it is.
Blog Posts

The bottleneck has moved.
.jpeg)
With MIG, we can partition RTX 6000 Pro cards into isolated 24 GB instances. Here's when it makes sense for your workloads.
.jpeg)
How 1,100 researchers beat OpenAI's own baseline with 16 megabytes and 10 minutes.