Change8

b8356

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

Summary

This release includes a critical bug fix in the ggml library related to IQ4_NL quantization and provides updated pre-compiled binaries for various operating systems and hardware configurations.

🐛 Bug Fixes

  • Guard against sumq2 being 0 in IQ4_NL quantization format.

Affected Symbols