5 Commits (e89ca5cc17bf9cccdaf24e5b4ac78c0b7183e7a2)

Author SHA1 Message Date
  Martin Evans bca55eace0 Initial changes to match the llama.cpp changes 2 years ago
  Martin Evans a9e6f21ab8 - Creating and destroying contexts in the stateless executor, saving memory. It now uses zero memory when not inferring! 2 years ago
  Martin Evans e2fe08a9a2 Added a higher level `LLamaWeights` wrapper around `SafeLlamaModelHandle` 2 years ago
  Martin Evans f31bdf6b93 Using the right context for Bob 2 years ago
  Martin Evans f3511e390f WIP demonstrating changes to support multi-context. You can see this in use in `TalkToYourself`, along with notes on what still needs improving. 2 years ago