Change8

b8058

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

Summary

This release introduces performance optimizations for the ggml CPU backend, specifically targeting the ggml_vec_dot_bf16 function on s390x architecture, alongside updated pre-compiled binaries.

✨ New Features

  • Optimized ggml_vec_dot_bf16 operation for s390x architecture.

Affected Symbols