bytedance / bytedance/Protenix

Support for Nvidia RTX 5070 Ti (Blackwell sm_120)

Open
#265 20 comments 0 reactions 0 assignees View on GitHub
good issue
Dominant language
Python
Stars
2.1k
Forks
310
PR merge metrics
No merged PRs in 30d

Description

I installed Protenix 1.0.6 in a conda environment on a Linux machine (Ubuntu 24.04) with an Nvidia RTX 5070 Ti GPU (Blackwell sm_120 architecture). Unfortunately, it appears that sm_120 is not supported by some of the package versions that are specified for the protenix installation (e.g., torch 2.7.1). What would I need to do to enable me to run protenix inferences on this machine so that the GPU could be used for accelerated computations? Thank you.

Contributor guide

Open the contributing guide

Research direction

No source file, test, or entry point is identified. Start by reviewing the Protenix installation constraints and the specified torch 2.7.1 version against the RTX 5070 Ti's sm_120 architecture on Ubuntu 24.04; done means Protenix inference runs with GPU acceleration on that machine.

Written by the indexing model from the issue text.

Assessment

Tech stack
linux, python, pytorch, ubuntu
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.