Support CUDA 12.8 in Docker nightlies.

[bdice]

This adds CUDA 12.8 Docker images to the nightly selector.

Depends on rapidsai/docker#728.

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Updated (UTC)
docs	✅ Ready (Inspect)	Visit Preview	Feb 7, 2025 8:40pm

[netlify]

✅ Deploy Preview for docs-rapids-ai ready!

Built without sensitive environment variables

Name	Link
🔨 Latest commit	ebb5c5c
🔍 Latest deploy log	https://app.netlify.com/sites/docs-rapids-ai/deploys/67a66f8eeafbc70008947796
😎 Deploy Preview	https://deploy-preview-571--docs-rapids-ai.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify site configuration.

[bdice]

There is a bug when selecting Nightly + Docker. I need it to change to a supported CUDA version. I will fix that.

[bdice]

Things should be working now. Ready for review.

[jakirkham]

Thanks Bradley! 🙏

Generally this looks good

Did notice one thing that I had a question on. Is CUDA 12.5 meant to be grayed out here?

Also guessing there will be some follow up work when stable becomes RAPIDS 25.02 and RAPIDS 25.04 is nightly

[bdice]

Is CUDA 12.5 meant to be grayed out here?

Yes. See rapidsai/docker#728 and #573.

[jakirkham]

Thanks Bradley! 🙏

Knew we were deprecating these in 25.04 with PR: #573

However was unaware they would be grayed out for 25.02 where they are still supported

[bdice]

Knew we were deprecating these in 25.04 with PR: #573
However was unaware they would be grayed out for 25.02 where they are still supported

@jakirkham The RSN is a little ambiguous. We will not ship CUDA 12.5 Docker images in 25.02. The "deprecation notice" is really just a removal/replacement with 12.8. The RSN reads:

RAPIDS is planning to deprecate support of CUDA 12.5 Docker containers in Release v25.02, and to cease publishing CUDA 12.5 Docker containers before the v25.02 release. The CUDA 12.5 containers will be replaced by CUDA 12.8 containers. We are continuing support for CUDA 11.8 and 12.0 containers.

[jakirkham]

Oh that was non-obvious. Thank you for clarifying! 🙏

Would suggest we title that differently to make it more clear they are going away soon: #573 (comment)

[bdice]

@jakirkham Can we approve this and let the RSN discussion be handled separately?

[jakirkham]

Thanks Bradley! 🙏