RaBitQ lands in Vectorium: up to 30x vector compression, 1.4-2.2x faster than PQ
CShorten30 · x · 2026-09-15
RaBitQ quantization is now integrated into Vectorium: up to 30x compression with no training required, flexible 1/2/4/8 bits per component, and 1.4-2.2x faster than the original implementation. On neural embeddings it beats PQ on every axis — compression, speed, and accuracy — with the gap widening as dimensionality grows.
More from Infra
- To dethrone Postgres, new databases must prioritize ecosystem integrations from day one — mgill25 · 2026-11-02
- ESP32-powered 4-inch touchscreen builds a TUI dashboard for monitoring a DGX inference cluster — CATLLM · 2026-11-02
- OpenRouter crosses 10 quadrillion annualized token run rate, doubling every 10.5 weeks — deedydas · 2026-11-02
- Palmer Luckey asks: can you use datacenter RAM for things prohibited by the operator's terms of service? — avaitopiper · 2026-11-02
- Disable MTP for 20-30% faster local LLM inference on limited RAM — InternalMode8159 · 2026-11-02
- Kioxia up 216% in a year but down 68% from its June 2026 peak — zephyr_z9 · 2026-11-02