Change8

b8117

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

Summary

This release focuses on enhancing CPU performance by adding support for various RVV vec dot kernels within ggml-cpu, alongside providing updated pre-compiled binaries for multiple operating systems and hardware configurations.

✨ New Features

  • Added RVV vec dot kernels for various quantization types (iq2_s, iq3_s, tq1_0, tq2_0, iq1_s, iq1_m) in ggml-cpu.
  • Added vlen switch for rvv vec_dot in ggml-cpu.

Affected Symbols