Tag

Turboquant

All articles tagged with #turboquant

markets2 hours ago•23 min saved

Google's TurboQuant memory boost shakes Micron's stock

Google's TurboQuant compression promises major memory savings for AI models, sparking a mixed market reaction as Micron and other memory makers slide on the expectation that AI efficiency could lower memory demand, even as some analysts warn the effect could eventually boost AI adoption and memory usage.

via MarketWatch|

#ai #google #markets

technology3 hours ago•5 min saved

Google's TurboQuant Slashes LLM Memory 6x Without Sacrificing Output

Google Research's TurboQuant uses PolarQuant and Quantized Johnson-Lindenstrauss (QJL) to compress the LLM key-value cache, quantizing to as little as 3 bits with no retraining and delivering up to 6x memory reduction and up to 8x faster attention logits at 4-bit, with perfect downstream results in tests on Gemma and Mistral.

via Ars Technica|

#ai-compression #google #llms