Change8

b9925

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

Summary

This release introduces support for f16->f16 GGML_OP_SET_ROWS in the CUDA backend and provides updated pre-compiled binaries for numerous platforms including macOS, Linux, Android, and Windows.

✨ New Features

  • Added support for f16->f16 GGML_OP_SET_ROWS operation in CUDA backend.

Affected Symbols