Change8

b10195

📦 llama-cppView on GitHub →
🐛 2 fixes🔧 1 symbols

Summary

This release includes improvements to testing by optimizing the build process for get-model.cpp and fixing quant type selection. It also provides pre-compiled binaries for various platforms and hardware accelerators.

Migration Steps

  1. Remove the get-model.cpp file from tests.

🐛 Bug Fixes

  • Fixed quant type selection in tests.
  • Avoided building get-model.cpp multiple times in tests.

Affected Symbols