A small error-correction signal keeps compressed vectors accurate, enabling broader, more precise AI retrieval.

The biggest memory burden for LLMs is the key-value cache, which stores conversational context as users interact with AI chatbots. The cache grows as conversations lengthen, ...

Artificial intelligence model compression startup Refiant AI said today it has raised $5 million in seed funding from VoLo Earth Ventures to try to put an end to the “arms race” that has ignited a ...

Google LLC has unveiled a technology called TurboQuant that can speed up artificial intelligence models and lower their ...

With TurboQuant, Google promises 'massive compression for large language models.' ...

Memory prices are plunging and stocks in memory companies are collapsing following news from Google Research of a ...

Google's TurboQuant combines PolarQuant with Quantized Johnson-Lindenstrauss correction to shrink memory use, raising ...

Google thinks it's found the answer, and it doesn't require more or better hardware. Originally detailed in an April 2025 paper, TurboQuant is an advanced compression algorithm that’s going viral over ...

Memory stocks continued to struggle in early trading Tuesday amid fears over Google's AI compression algorithm.

Within 24 hours of the release, community members began porting the algorithm to popular local AI libraries like MLX for Apple Silicon and llama.cpp.

Make AI work smarter, not harder.