Change8

b10243

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

Summary

This release focuses on optimizing memory usage by allocating the indexer cache only in "full" indexer layers. It also provides pre-compiled binaries for various platforms and hardware configurations.

🐛 Bug Fixes

  • Allocate indexer cache only in "full" indexer layers.

Affected Symbols