sokrypton / sokrypton/ColabFold
Keep Jax compiled
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 2.9k
- Forks
- 747
- PR merge metrics
- No merged PRs in 30d
Description
First of all thanks for the great work! I really appreciate colabfold!
I am running colabfold (localcolabfold) on a GPU cluster. Using the 'turbo' mode works great when applied to models after the first model is compiled (First model around 2 min for a 100aa protein, following 4 models only 1-5s each) which is awesome, but I was wondering if there is a way to 'keep Jax compiled' for following predictions of proteins the same length to keep all models running at 1-5s.
Just deleting the 'done.txt' and predicting the same .fasta file in the output directory doesnt work, so I was wondering if this is not possible or if I am missing something.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No source file, test, or entry point is identified. Start by tracing turbo mode and the done.txt handling in localcolabfold, then determine whether compiled JAX state can persist between predictions of the same length; done means subsequent predictions reuse the compilation rather than recompiling.
Written by the indexing model from the issue text.
Assessment
- Domain
- bioinformatics, machine-learning, performance
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100