Back to Freedom.Tech Back
All llama.cpp releasesAll versions
Release Wed, May 13, 2026 1 min read

llama.cpp b9129

Original release notes

ggml-zendnn : adaptive fallback to CPU backend for small batch sizes (#22681)

  • ggml-zendnn : add runtime env var GGML_ZENDNN_ADAPTIVE_FALLBACK to control adaptive fallback (default: enabled)
  • ggml-zendnn : restore original fallback logic when adaptive fallback is disabled