Change8

b9934

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

Summary

This release focuses on performance tuning for the ggml-webgpu backend by adjusting the flash attention subgroup split parameter. It also provides a comprehensive set of pre-compiled binaries for diverse platforms.

✨ New Features

  • Tuned subgroup split (d_split) in flash_attn_vec for ggml-webgpu backend.

Affected Symbols