Change8

b8967

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

Summary

This release primarily reposts binaries, highlighting the addition of Blackwell native NVFP4 support for ggml-cuda, alongside numerous pre-compiled binaries for diverse operating systems and hardware configurations.

✨ New Features

  • Added Blackwell native NVFP4 support for ggml-cuda.

Affected Symbols