
TurboQuant: Google'ın LLM Belleğini 6x Küçülten Sıkıştırma Algoritması
Google Research bu hafta TurboQuant'ı duyurdu: LLM'lerin KV cache belleğini 6 kat küçülten, NVIDIA H100'de 8 kata kadar hız artışı sağlayan ve bunu sıfır accura

iOS Developer crafting apps with Swift & SwiftUI
Thoughts on AI, software, and technology
I'm always open to discussing new projects, creative ideas, or opportunities to be part of your visions.
Interested in working together? We should queue up a time to chat. I'll buy the coffee.
Let's do this