fix: bugs - Githubissues

withcatai / node-llama-cpp

Run AI models locally on your machine with node.js bindings for llama.cpp. Force a JSON schema on the model output on the generation level

https://node-llama-cpp.withcat.ai

MIT License

829 stars 80 forks source link

fix: bugs #80

Closed giladgd closed 10 months ago

giladgd commented 10 months ago

Description of change

feat: adapt to the latest llama.cpp interface
feat: print helpful information to help resolve a clone issue when it happens
feat: print helpful information to help resolve build issues related to CUDA
feat: make portable cmake on Windows more stable
feat: update CMakeLists.txt to match llama.cpp better
fix: do not download redundant node headers
fix: improve cmake custom options handling
fix: do not set CMAKE_GENERATOR_TOOLSET for CUDA
fix: do not fetch information from GitHub when using a local git bundle
fix: GBNF JSON schema string const formatting
docs: document a solution to a compilation problem on macOS
docs: document more CUDA build error solutions
docs: explain about ES modules in the getting started guide
chore: update .commitlintrc.json
chore: remove redundant dependency

Fixes #78 Fixes #79 Fixes #58 Reintroduces #74 - added documentation on how to resolve it (link)

Pull-Request Checklist

[x] Code is up-to-date with the master branch
[x] npm run format to apply eslint formatting
[x] npm run test passes with this change
[x] This pull request links relevant issues as Fixes #0000
[x] There are new or updated unit tests validating the change
[x] Documentation has been updated to reflect this change
[x] The new commits and pull request title follow conventions explained in pull request guidelines (PRs that do not follow this convention will not be merged)

github-actions[bot] commented 10 months ago

:tada: This PR is included in version 2.7.4 :tada:

The release is available on:

Your semantic-release bot :package::rocket: