Google researchers have published a new quantization technique called TurboQuant that compresses the key-value (KV) cache in large language models to 3.5 bits per channel, cutting memory consumption ...

Google has published TurboQuant, a KV cache compression algorithm that cuts LLM memory usage by 6x with zero accuracy loss, ...

Forget the parameter race. Google's TurboQuant research compresses AI memory by 6x with zero accuracy loss. It's not available yet, but it points to where AI efficiency is headed.

MIT researchers developed Attention Matching, a KV cache compaction technique that compresses LLM memory by 50x in seconds — without the hours of GPU training that prior methods required.