Change8

b8937

📦 llama-cppView on GitHub →
1 features🔧 1 symbols

Summary

This release re-enables the fast gelu_quick_f16 optimization for ggml-cpu builds and provides a comprehensive set of pre-compiled binaries across various operating systems and hardware configurations.

✨ New Features

  • Re-enabled fast gelu_quick_f16 computation for ggml-cpu.

Affected Symbols