0.1.63

What's Changed

• Bumped version to 0.1.63 by @github-actions in #397
• Bump zerovec-derive from 0.10.2 to 0.10.3 by @dependabot in #392
• Simplify CPU features: just detect them in build.rs instead of exposing them as crate features by @babichjacob in #404
• Enlarge the buffer in LlamaModel::apply_chat_template by @babichjacob in #410
• BREAKING: Add a variant to ChatTemplateError and LlamaModel::get_chat_template for when the user specifies too small of a buffer by @babichjacob in #412
• Bump clap from 4.5.8 to 4.5.9 by @dependabot in #405
• Update llama cpp [MAC TESTING WANTED] by @MarcusDunn in #400
• macOS build.rs fixes to align w ggml-org/llama.cpp@f3f6542 by @brittlewis12 in #417

New Contributors

• @brittlewis12 made their first contribution in #417

Full Changelog: 0.1.62...0.1.63