• Fixes #19
• Updates llama.cpp submodule

• Adds support for "infinite text generation" using context swapping (similar to the main example in llama.cpp)

• Makes unit tests more consistent and usable (still not running in workflows as the weights are too large)
• Updates llama.cpp submodule

• Breaking change but makes model loading practically instantaneous thanks to memory-mapped I/O
• Requires re-generating the weight files using the new convert script (or use the migration script from llama.cpp)

• Adds back get_tokenizer() and add_bos() that were broken in previous release

• Updates the bindings to work with the new llama.cpp API from ggerganov/llama.cpp#370
• Adds two separate interfaces - LlamaInference which is similar to the bindings in v0.1.8 and the lower level LlamaContext (currently untested)
• The old bindings are still present in PyLlama.cpp but is currently not compiled and will be removed at a later date

• Adds a "tokenizer" object for use with oobabooga/text-generation-webui

• Switches from poetry to scikit-build as the build tool due to problems with cross-compiling on CI
• Adds CI builds for macOS arm64 wheels
• Adds windows wheel files to PyPI built on CI

• Fixes windows builds on CI (hopefully).
• Removes torch and sentencepiece as dependencies. They have to be manually installed now if you want to use llamacpp-convert

Includes new llamacpp-cli and llamacpp-chat entrypoints. There's possibly still some kind of bug that makes the performance of llamacpp-chat a bit worse than if you passed in the arguments directly into llamacpp-cli