latenceainew/colsearch

High-performance late-interaction retrieval engine for on-prem AI. ColBERT/ColPali multi-vector search with Rust fused MaxSim, Triton GPU kernels, ROQ quantization, LEMUR routing, WAL-backed CRUD, and a FastAPI server — single machine, CPU or GPU.

17
Stars
1
Forks
19.8
Radar Score
Declining
Momentum

Scoring Breakdown

Impact4.8
Velocity19.9
Health43.5

Growth Metrics

7-Day Stars
+0
30-Day Stars
+0
Acceleration
x
Language
Python

Why it ranks

Modest but positive momentum.

AI Infrastructure · model servingTop 97% globally
View on GitHub