Benchmark reliability of torchbenchmarks
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1k
- Forks
- 346
- PR merge metrics
- No merged PRs in 30d
Description
Recently I found that for the same model, the native benchmark code in torchbenchmarks does not give expected time, i.e. one is consistently slower than the other one, or one could be slower by up to 20%, I'm relying on torchao.utils.benchmark_model for now, please help take a look to see what might be the problem.
For details please see: https://github.com/pytorch/benchmark/pull/2519
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
Start by reviewing PR #2519 and comparing the native torchbenchmarks benchmark code with torchao.utils.benchmark_model for the same model. Identify why the reported timings diverge by up to 20%, then validate the explanation with repeatable benchmark results showing consistent timing between the implementations.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100