Change8

b9888

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

Summary

This release enhances CUDA flash attention by extending K-type validation to V-types and provides updated pre-compiled binaries across multiple operating systems and hardware configurations.

✨ New Features

  • Extended K-type validation to V-types for flash attention in CUDA kernels.

Affected Symbols