Google's TurboQuant Just Wiped Billions From Memory Chip Stocks — And It's Only Getting Started
Micron just lost over $100 per share. Samsung shed 5%. DDR5 prices dropped 30%. The culprit? A compression algorithm from Google Research that makes AI models need dramatically less memory. And it hasn’t even shipped as a product yet. The DeepSeek Sequel Nobody Expected TurboQuant does something deceptively simple: it compresses the key-value cache — the short-term memory AI models use during inference — by 6x while making inference 8x faster. Zero accuracy loss. No retraining. No fine-tuning. Just plug it into your existing pipeline. ...