Change8

b9855

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

Summary

This release introduces performance improvements to ggml-cpu by adding AVX2 optimization for nvfp4 dot product and integrating UE4M3 LUTs. Various pre-compiled binaries for different platforms are provided.

✨ New Features

  • Added AVX2 optimization for nvfp4 dot product in ggml-cpu.
  • Added UE4M3 LUT usage for nvfp4 dot product in ggml-cpu.

Affected Symbols