Nature-inspired optimisation techniques have revolutionised image compression by emulating collective behaviours and evolutionary processes observed in biological and physical systems. Central to many ...

turboquant-py implements the TurboQuant and QJL vector quantization algorithms from Google Research (ICLR 2026 / AISTATS 2026). It compresses high-dimensional floating-point vectors to 1-4 bits per ...

The big picture: Google has developed three AI compression algorithms – TurboQuant, PolarQuant, and Quantized Johnson-Lindenstrauss – designed to significantly reduce the memory footprint of large ...

This voice experience is generated by AI. Learn more. This voice experience is generated by AI. Learn more. On March 24, 2026 Amir Zandieh and Vahab Mirrokni from Google Research published an article ...

Running a 70-billion-parameter large language model for 512 concurrent users can consume 512 GB of cache memory alone, nearly four times the memory needed for the model weights themselves. Google on ...

If Google’s AI researchers had a sense of humor, they would have called TurboQuant, the new, ultra-efficient AI memory compression algorithm announced Tuesday, “Pied Piper” — or, at least that’s what ...

As Large Language Models (LLMs) expand their context windows to process massive documents and intricate conversations, they encounter a brutal hardware reality known as the "Key-Value (KV) cache ...

The scaling of Large Language Models (LLMs) is increasingly constrained by memory communication overhead between High-Bandwidth Memory (HBM) and SRAM. Specifically, the Key-Value (KV) cache size ...

AI has a growing memory problem. 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 ...

Abstract: In this paper, we demonstrate the superiority of Block Adaptive Vector Quantization (BAVQ) over conventional scalar Block Adaptive Quantization (BAQ) for compressing the on-board ...

Vector Post-Training Quantization (VPTQ) is a novel Post-Training Quantization method that leverages Vector Quantization to high accuracy on LLMs at an extremely low bit-width (<2-bit). VPTQ can ...