Back to Freedom.Tech Back
All llama.cpp releasesAll versions
Release Sun, Oct 4, 2026 1 min read

llama.cpp b11398

Original release notes

ggml-cpu: support BF16/FP16/FP32 K tails in tinyBLAS on x86 (#29806)

  • ggml-cpu: vectorize BF16 K tails in tinyBLAS
  • tests: Skip tinyBLAS when use_ref is enabled so CPU tests compare against the vec_dot path.
  • ggml-cpu: vectorize tinyBLAS F16/F32 tails

Website: -

Attestations: -

UI: