Skip to content

“So something like Olama or Llama.cpp, they'll do that…” — The Vergecast at 58:53

The Vergecast We unfolded the iPhone Duo

“So something like Olama or Llama.cpp, they'll do that automatically. They'll take the encoder, the decoder layers, the KV cache and stick that on the GPUs, run everything else out of the system RAM.”

0:00 1:17:42