inlinedio/ikv-store

High-performance key-value store for ML inference. 100x faster than Redis.

32
/ 100
Emerging

This is a high-performance, cost-effective key-value store specifically designed for machine learning inference. It ingests large datasets of ML features and provides ultra-fast retrieval, enabling real-time predictions for applications like recommendation engines or search. Data scientists, machine learning engineers, and application developers working on low-latency prediction services would use this.

226 stars. No commits in the last 6 months.

Use this if you need sub-millisecond data retrieval for ML features or general-purpose caching, especially when your current database solutions like Redis are too slow or costly for high-volume reads.

Not ideal if your application requires immediate read-after-write consistency or if your primary goal is to store and frequently update transactional data.

Machine Learning Inference Real-time Predictions Feature Store High-Performance Caching Recommendation Systems
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

226

Forks

4

Language

Rust

License

MIT

Last pushed

May 14, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/inlinedio/ikv-store"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.