Universal I/O in Qdrant
How Qdrant talks to different storage backends through a unified I/O interface
Luis Cossío, Clelia Bertelli
October 12, 2026
Qdrant Internals
Take a look under the hood of Qdrant’s high-performance vector search engine. Explore the architecture, components, and design principles the Qdrant Vector Search Engine is built on.
Filtered Vector Search: What ACORN Fixes, and What Fixes ACORN
ACORN repairs filtered HNSW search at query time, extra edges at index time. We benchmarked both in Qdrant on one million points.
Dylan Couzon & Meina Ghafouri
August 7, 2026
Introducing Gridstore: Qdrant's Custom Key-Value Store
Why and how we built our own key-value store.
Luis Cossio, Arnaud Gourlay & David Myriel
February 5, 2025
Immutable Data Structures in Qdrant
Learn how immutable data structures improve vector search performance in Qdrant.
Andrey Vasnetsov
August 20, 2024
Faster Disk I/O for Vector Search Using io_uring
The Linux io_uring API offers great performance in certain cases. Here's how Qdrant uses it!
Andre Bogus
June 21, 2023
Filterable HNSW Without Recall Loss
How to make ANN search with custom filtering?
Andrei Vasnetsov
November 24, 2019