Qdrant is launching version 1.18 of its platform, introducing TurboQuant, a new quantization method developed by Google Research.
According to the company, TurboQuant applies a fast Hadamard rotation to vectors before compression, which redistributes values evenly across coordinates. Because this rotation normalizes the data distribution, TurboQuant works well with any embedding model.
Other main features include:
- Memory Monitoring: Inspect a collection’s disk, RAM, and page cache usage broken down by component (vectors, payload, indexes, and more) via a new Web UI view and API endpoint.
- Adding and Removing Named Vectors: Add or remove named vectors to an existing collection’s schema without having to recreate it.
Qdrant’s implementation of TurboQuant extends the original algorithm to close the gap between the algorithm’s theoretical assumptions and real-world embeddings. A length renormalization step corrects a recall-degrading bias caused by quantization error, an idea borrowed from RaBitQ, the company said.
Additionally, version 1.18 adds two improvements to audit logging: a new API endpoint to query audit logs, and support for request tracing IDs. It also introduces per-collection API metrics and two new strict mode guardrails.
A per-coordinate calibration pre-pass fits the data to precomputed codebooks, aiming to recover accuracy lost to distribution mismatch. Cosine, dot product, and L2 are all supported as first-class distance metrics. And finally, the compnay implemented highly optimized SIMD acceleration for TurboQuant to achieve maximum performance.
This release introduces collection memory monitoring, offering a detailed breakdown of disk, RAM, and OS page cache usage per component, summed across the whole cluster. The same data is available through Qdrant’s API.
Version 1.18 makes it possible to add and remove named vectors to an existing collection’s schema without having to recreate it. This makes embedding model migration considerably easier. You can now add a new vector field, populate it in the background, and remove the old one when you’re ready, said the vendor.
Audit logging was introduced in Qdrant 1.17 to track API operations. Version 1.18 adds two improvements: a new API endpoint to query audit logs, and support for attaching tracing IDs to requests.
For more information about this news, visit https://qdrant.tech.