Change8

b9733

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

Summary

This release introduces F16 adapter toggles for Vulkan/NVIDIA in ggml-webgpu and provides numerous pre-compiled binaries across different platforms and hardware accelerators.

✨ New Features

  • Added adapter toggles for F16 support on Vulkan with NVIDIA hardware in ggml-webgpu.

Affected Symbols