RosettaCommons / RosettaCommons/RFdiffusion

Channel order causes CPU pytorch to be installed

Open
#119 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.1k
Forks
644
PR merge metrics
No merged PRs in 30d

Description

The channel order in the conda environment file puts conda-forge ahead of pytorch:
https://github.com/RosettaCommons/RFdiffusion/blob/ba8446eae0fb80c121829a67d3464772cc827f01/env/SE3nv.yml#L2-L7

This means that the conda-forge version of packages will be installed in preference to pytorch, at least using micromamba which I tested this with. This means that a GPU will not get utilized.

Can this file be updated to put pytorch at higher priority? Thanks

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Open env/SE3nv.yml at lines 2-7 and inspect the channel order. Reproduce the dependency resolution with micromamba, then update the ordering so the PyTorch channel has higher priority. Done means the environment resolves to the GPU-enabled PyTorch packages rather than the conda-forge CPU version.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
devops, machine-learning
Issue type
Bug
Difficulty
1/5
Estimated time
Under an hour
Activity status
Stale
Clarity
Clearly specified
Newbie friendliness
55/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.