2026-04-28 13:14 UTC
Impressive:
“TurboQuant: Redefining AI Efficiency With Extreme Compression”, Amir Zandieh, et al, Google Research (https://research.google/blog/turboquant-redefining-ai-efficiency-with-extreme-compression/).
The paper: https://arxiv.org/abs/2504.19874
On HN: https://news.ycombinator.com/item?id=47513475
#TurboQuant #Quantization #LLMs #Vectors #Compression #Paper
Replies (1)
-
@rmathew@mastodon.social 2026-04-29 13:19
An excellent introduction to #quantization used for #LLMs 👌🏽: “Quantization From The Ground Up”, Sam Rose, Ngrok (https://ngrok.com/blog/quantization). On HN: https://news.ycombinator.com/item?id=47519295 #AI #Math #FloatingPoint #NumericalAnalysis #Numbers #NeuralNetworks #Precision #Accuracy