Change8

b8352

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

Summary

This release introduces NVFP4 tensor support for Qwen3.5 and Qwen3.5MoE models. It also provides a comprehensive set of pre-compiled binaries for numerous platforms and hardware accelerators.

✨ New Features

  • Added support for Qwen3.5 and Qwen3.5MoE tensors with NVFP4 quantization.

Affected Symbols