Back to Freedom.Tech Back
All llama.cpp releasesAll versions
Release Sun, Aug 2, 2026 1 min read

llama.cpp b10232

Original release notes

metal: implement DeepSeek V4 hyper-connections (#26459)

  • Implement GGML_OP_DSV4_HC_COMB, GGML_OP_DSV4_HC_PRE, and

GGML_OP_DSV4_HC_POST with SIMDgroup register and shuffle optimized kernels.

  • Add Metal dispatch and support plumbing and test the production Sinkhorn

iteration count and embedding width.

Assisted-by: Codex

Co-authored-by: Thiago Padilha

Website: -

UI: