Add Blackwell GPU support using NVIDIA PyTorch container #26
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
|
This looks great, thank you so much @eidamo ! I'll also keep you posted on future updates to the docker recipe in case it affects your work on Blackwell GPUs. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes #22
Summary
This PR adds support for NVIDIA Blackwell GPUs (compute capability 12.0) to OpenFold-3 by providing an alternative Dockerfile that uses the NVIDIA PyTorch container as a base image.
Changes
Motivation
The current Dockerfile uses nvidia/cuda:12.1.1-cudnn8-devel-ubuntu22.04, which doesn't natively support Blackwell architecture. The NVIDIA PyTorch container provides out-of-the-box compatibility with newer GPU architectures.
Testing
✅ Successfully built Docker image for Blackwell GPU
⚠️ Backward compatibility with older GPU architectures not yet verified
✅ Inference runs successfully on NVIDIA RTX PRO 6000 Blackwell (compute capability 12.0)
❌ Training has not been tested
Usage
docker build -f Dockerfile.blackwell -t openfold-3-blackwell:latest .