Data Science Wire

Qdrant 1.19 - TurboQuant Datatype & Memory Tiers

Qdrant Blog1mo4 min read

Qdrant 1.19.0 is out! Let’s look at the main features for this version: TurboQuant Datatype: A new storage format that compresses vectors to four bits without keeping their original full-precision representation, reducing storage by up to nine times compared to TurboQuant quantization. Memory Tiers: A single memory parameter unifies per-component memory tier placement, with three tiers: pinned , cached , and cold . Per-Tenant IDF Statistics: Narrow the IDF corpus to a specific tenant so term rarity reflects that tenant’s vocabulary rather than the whole dataset, improving BM25 scoring in multi

Read the full story at Qdrant Blog

More in MLOps / LLMOps