Memory Chips

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. ...

Remember Pied Piper from HBO’s Silicon Valley? The fictional startup that built a compression algorithm so good it basically broke the internet? Google just built the real thing. Except instead of compressing video files, it’s compressing AI’s brain. On Tuesday, Google Research unveiled TurboQuant, a compression algorithm that reduces the memory footprint of large language models by at least 6x while delivering up to 8x faster performance on Nvidia H100 GPUs. The kicker: zero accuracy loss. ...