Change8

b8526

📦 llama-cppView on GitHub →
1 features

Summary

This release introduces support for the codefuse-ai/F2LLM-v2 model and provides a comprehensive set of pre-compiled binaries for numerous platforms including specific CUDA, ROCm, Vulkan, and specialized hardware targets.

✨ New Features

  • Added support for model: codefuse-ai/F2LLM-v2.