Google Research@GoogleResearchIntroducing TurboQuant: Our new compression algorithm that reduces LLM key-value cache memory by at least 6x and delivers up to 8x speedup, all with zero accuracy loss, redefining AI efficiency. Read the blog to learn how it achieves these results: t.coOpens with an announcement
Google Research@GoogleResearchIntroducing the FACTS Benchmark Suite, developed by @GoogleDeepMind & @GoogleResearch to produce a comprehensive test measuring LLM factuality across four dimensions: internal model knowledge, web search, grounding, & multimodal inputs. More on the blog →t.coOpens with an announcement