ggerganov/llama.cpp Released Version b12423
llama.cpp release b12423 has been published, featuring a revert of a recent commit regarding jinja template features. This update rolls back the addition of four missing jinja template features that were introduced in commit a681a53. This routine maintenance release ensures the stability of template parsing in the library by removing potentially unstable or problematic changes. It highlights the fast-paced development and continuous refinement typical of core infrastructure libraries in the AI ecosystem. The release specifically reverts commit a681a53b6092d57597b9e66f2fc9d4556155b9e4, which previously attempted to add four missing features to the jinja template support. Binary packages across various platforms such as macOS, Linux, and Windows remain available for deployment.
## BACKGROUND
llama.cpp is an open-source software library created by Georgi Gerganov that performs local inference on various large language models using C and C++. It works alongside the GGML tensor library and serves as the foundation for numerous popular local AI applications and tools.