Change8

b9313

📦 llama-cppView on GitHub →
1 features🔧 5 symbols

Summary

This release introduces performance enhancements to ggml by parallelizing the initialization of quantization look-up tables using OpenMP. It also provides numerous pre-built binaries for various operating systems and hardware configurations.

Migration Steps

  1. Update OpenMP dependencies in ggml-config.cmake.in if you build from source.

✨ New Features

  • Parallelized initialization of quant LUTs (iq2xs_init_impl and iq3xs_init_impl) using OpenMP in ggml.

Affected Symbols