myrmidon

↗ HN profile [ 59.7 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. My understanding is that current LLMs require a lot of space for pre-computed weights (that are constant at inference-time). Why is it currently not feasible to just keep those in flash memory (fast PCIe SSD Raid or…

  2. Reuters: https://www.reuters.com/world/europe/what-is-intercontinental-ballistic-missile-ukraine-says-russia-fired-2024-11-21/ Impact video (low quality):…