Change8

b10188

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

Summary

This release addresses a memory leak in the metal backend when models are freed without GPU operations. It also provides pre-compiled binaries for various platforms and hardware configurations.

🐛 Bug Fixes

  • Fixed a memory leak in the metal backend that occurred when a model was freed without any GPU operations.

Affected Symbols