| ▲ | Google's TurboQuant AI-compression algorithm can reduce LLM memory usage by 6x(arstechnica.com) | |||||||
| 17 points by gmays a day ago | 2 comments | ||||||||
| ▲ | redanddead a day ago | parent [-] | |||||||
You'd think it'd be bigger news on hn | ||||||||
| ||||||||
| ▲ | Google's TurboQuant AI-compression algorithm can reduce LLM memory usage by 6x(arstechnica.com) | |||||||
| 17 points by gmays a day ago | 2 comments | ||||||||
| ▲ | redanddead a day ago | parent [-] | |||||||
You'd think it'd be bigger news on hn | ||||||||
| ||||||||