Back to Freedom.Tech Back
All llama.cpp releasesAll versions
Release Tue, Sep 15, 2026 1 min read

llama.cpp b10988

Original release notes

opencl: choose the MoE expert matmul by batch size for speculative decoding/MTP (#27637)

  • opencl: gate the prebuilt q4_0 MoE GEMM on routing count
  • opencl: stop writing zeros into the padded MoE activation slots
  • opencl: rephrase claude's comments

---------

Co-authored-by: Li He

Website: -

Attestations: -

UI: