mlcommons / mlcommons/inference
[Performance] Slow loading of MM datas
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.6k
- Forks
- 650
- Avg merge
- 1d 22h
- Merged PRs (30d)
- 6
Description
In _load_samples_to_ram and calls formulate_loaded_sample.
Parallelize with ThreadPoolExecutor. For the Shopify benchmark, it can take up to 240s, which is unnecessary.
Also, it should use pybase64 for encode and decode
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 locating _load_samples_to_ram and its calls to formulate_loaded_sample, then run the Shopify benchmark to observe the loading time. Evaluate the proposed ThreadPoolExecutor parallelization and pybase64 encoding/decoding; done means the benchmark loads samples faster without changing results.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100