Google Research details TurboQuant, a quantization algorithm to enable massive compression of LLMs and vector search engines without sacrificing accuracy (Google Research)

Google Research: Google Research details TurboQuant, a quantization algorithm to enable massive compression of LLMs and vector search engines without sacrificing accuracy — Amir Zandieh, Research Scientist, and Vahab Mirrokni, VP and Google Fellow, Google Research — We introduce a set …