←back to thread

SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators

(machinelearning.apple.com)
171 points pizza | 1 comments | 4/6/2025, 8:53:00 AM | HN request time: 0.201s | source
Show context
anshumankmr ◴[4/6/2025, 10:12:00 AM] No.43600316[source]▶

all this and they can't launch Apple intelligence on schedule :(

replies(3): >>43600352 #>>43602277 #>>43602445 #
timschmidt ◴[4/6/2025, 10:20:00 AM] No.43600352[source]▶

Honestly, this seems like enabling work. Even the iPhone 16 Pro Max only seems to have 8GB RAM. If Apple Intelligence plans to do anything useful on-device, they need work like this.

replies(1): >>43602731 #
1. manmal ◴[4/6/2025, 4:32:00 PM] No.43602731[source]▶

Personally, I‘m holding off on purchasing a new iPhone for this reason, even though my 13 Pro is getting long in the tooth as a full time iOS dev. The coming generation is rumored to have more and better memory (LPDDR5X?), and cooling (vapor chamber).