←back to thread

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

(machinelearning.apple.com)
171 points pizza | 5 comments | 06 Apr 25 08:53 UTC | HN request time: 0.257s | source
1. anshumankmr ◴[06 Apr 25 10:12 UTC] No.43600316[source]▶
all this and they can't launch Apple intelligence on schedule :(
replies(3): >>43600352 #>>43602277 #>>43602445 #
2. timschmidt ◴[06 Apr 25 10:20 UTC] 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 #
3. brookst ◴[06 Apr 25 15:44 UTC] No.43602277[source]▶
Research vs productization. Very different.
4. echelon ◴[06 Apr 25 16:01 UTC] No.43602445[source]▶
This unblocks future product work. You have to lay the groundwork.

We need advancements like this if we want on-device AI to work well. This is the kind of thing Apple Silicon needs especially. It's weak relative to Nvidia consumer chips.

5. manmal ◴[06 Apr 25 16:32 UTC] 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).