[Question] on an M2 Max FastEmbed is way slower than SentenceTransformers
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.2k
- Forks
- 248
- Avg merge
- 4d 8h
- Merged PRs (30d)
- 4
Description
I'm comparing embedding performances comparing FastEmbed vs SentenceTransformers, and in my experiment, it turns out that FastEmbed is way slower than SentenceTransformers.
See a complete working example at my GitHub repo
Even if I disable GPU for SentenceTransformers (utils.py --> _pick_device --> make it return "cpu" only) it is still way faster than Fastembedd.
Can someone take a look at it? Maybe I'm doing something wrong.
Tested on an M2 Max 32Gb
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 running the complete working example in the linked qdrant-sample repository and inspect utils.py, especially _pick_device, as described in the issue. Compare FastEmbed with SentenceTransformers on the M2 Max under CPU-only settings. Done means identifying whether the comparison is configured correctly and documenting the cause of the performance difference.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100