michaelfeil / michaelfeil/infinity
[Benchmark] - embedding quantization
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.9k
- Forks
- 206
- PR merge metrics
- No merged PRs in 30d
Description
### System Info
0.0.40 shipped the first version of embedding quant.
`--embedding-dtype int8`
This Issue is looking for testers, to verify the real life performance of these features at real datasets.
### Information
- [X] Docker
- [X] The CLI directly via pip
### Tasks
- [X] An officially supported command
- [ ] My own modifications
### Reproduction
-
### Expected behavior
E.g. delivering a benchmark of int8 quantization - can be added under `./docs`
Contributor guide
No contributing guide indexed for this repository
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 officially supported command with --embedding-dtype int8 through Docker or the CLI installed via pip. Use real datasets to measure the feature's performance, then document the benchmark under ./docs; the issue does not specify which datasets or metrics to use.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- docker, python
- Domain
- documentation, machine-learning, performance
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100