Merge pull request #13 from jolexxa/feat/batching

feat: batching

Merge pull request #12 from jolexxa/fix/prefix-caching-llama.cpp

fix: prefix caching llama.cpp

fix: release

Merge pull request #7 from jolexxa/feat/model-loading

feat: show model loading progress

Merge pull request #6 from jolexxa/refactor/tidy

refactor: tidy everything up

feat: install script

fix: release workflow