github ggml-org/llama.cpp b7988

3 hours ago
Details

ggml-cpu: arm64: q6_K repack gemm and gemv (and generic) implementations (dotprod) (#19360)

  • First working version of GEMM and GEMV

  • interleave loads and compute

  • Clang-format

  • Added missing fallback. Removed tested TODO.

  • Swap M and N to be consistent with the repack template convention

macOS/iOS:

Linux:

Windows:

openEuler:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.