sokrypton / sokrypton/ColabFold
Is GPU or high-memory + CPU better for mmseqs2 server?
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 2.9k
- Forks
- 747
- PR merge metrics
- No merged PRs in 30d
Description
I'm looking into purchasing a dedicated machine to act as an mmseqs2 server for my organization.
What is the current recommendation for specifications? Is it faster to run in CPU mode with 1 TB memory, or on a recent GPU?
Here are the two options I'm considering:
- 1 TB RAM server with no GPU and run MMSeqs2 on CPU mode.
- 256 GB RAM, plus an NVIDIA RTX PRO 6000 GPU.
Other specs would be similar, i.e. some recent server CPU plus a large recent SSD.
Is either of these options clearly better than the other. Is there some other option I should prefer?
Thanks!
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
The issue names no repository files, tests, or entry points. Start by reviewing MMseqs2 CPU and GPU execution guidance and comparing the two proposed hardware configurations with representative benchmarks; done would be a supported recommendation that addresses the alternatives and any preferable option.
Written by the indexing model from the issue text.
Assessment
- Domain
- bioinformatics, performance
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 18/100