mirror of
https://github.com/ruvnet/RuVector.git
synced 2026-05-22 11:26:34 +00:00
a1a04a3570
First benchmark comparing all ruvector-core quantization methods against TurboQuant on standard vector search datasets. 8 configurations, 3 datasets (GloVe d=200, SIFT d=128, PKM d=384), 3 trials per config with variance. Key findings: - Int4 beats TurboQuant MSE on recall at 8x compression (91.2% vs 89.6% R@1) - QJL correction hurts recall for vector search (9-41% loss) - PQ with 8 subspaces fails at d=200 (18.2% R@1) - TurboQuant MSE 3-bit fills unserved 10.7x compression tier (82.0% R@1) - QuantizedVector::distance() never called during HNSW search Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| docs | ||
| graph | ||
| src | ||
| vector-search | ||
| .dockerignore | ||
| .gitignore | ||
| Dockerfile | ||
| package.json | ||
| setup.sh | ||
| visualization-dashboard.html | ||