Skip to content

ggmlv0.11.1

Updated

Tensor library for machine learning

#License

MIT

#Supported Platforms

!uwp

  • ✅linux
  • ✅osx
  • ✅windows
  • ❌uwp

#Features

No default features.

#blas

Enable BLAS support

Dependencies:
and one transitive dependency:
Host Dependencies:
2 transitive dependencies:

#cuda

Enable CUDA support

Platforms: !(windows & staticcrt)
  • ✅linux
  • ✅osx
  • ✅windows
    Dependencies:

    No transitive dependencies.

    Host Dependencies:

    No dependencies.

    #metal

    Enable Metal support

    Platforms: osx
    • ✅osx
    • ❌linux
    • ❌windows
    Dependencies:

    No dependencies.

    Host Dependencies:

    No dependencies.

    #opencl

    Enable OpenCL support

    Platforms: !arm32
    • ✅linux
    • ✅osx
    • ✅windows
      Dependencies:

      No transitive dependencies.

      Host Dependencies:
      2 transitive dependencies:

      #openmp

      Enable OpenMP support

      Platforms: !osx
      • ✅linux
      • ✅windows
      • ❌osx
      Dependencies:

      No dependencies.

      Host Dependencies:

      No dependencies.

      #vulkan

      Enable Vulkan support

      Dependencies:
      and 2 transitive dependencies:
      Host Dependencies:
      and 4 transitive dependencies:

      #Dependencies

      No dependencies.

      #Host Dependencies

      No transitive dependencies.

      #Used By

      #Host Tool For

      #Contributors

      • Stefano Sinigardi's avatarStefano Sinigardi
      • Kai Pastor's avatarKai Pastor
      • talregev's avatartalregev
      • Ankur Verma's avatarAnkur Verma
      • Chris Sarbora's avatarChris Sarbora
      • Billy O'Neal's avatarBilly O'Neal
      • miyan's avatarmiyan
      • Weihang Ding's avatarWeihang Ding
      • Reeshabh Choudhary's avatarReeshabh Choudhary

      #Changelog

      • 1d8862c
        1d8862c[ggml] Remove CPU feature detection (Fixes #53372) (#53482)
      • 4b3403c
        4b3403c[ggml] Update to 0.11.1 (#51693)
      • 68fb1ad
        68fb1adggml update to 0.11.0， llama-cpp update to 9030 (#51551)
      • f660f80
        f660f80[ggml] Support CUDA 13.2 on Windows. Fix patch whitespace errors. (#51458)
      • ab2977b
        ab2977b[vulkan, spirv, etc] Update to v1.4.328 (#48304)
      • 3da674f
        3da674f[llama-cpp,ggml] Update to llama-cpp: 7146 and ggml: 2025-11-17 (#48525)
      • 73af4de
        73af4de[ggml] Remove unnecessary patch (#47691)
      • e62a246
        e62a246[ggml] update to v0.9.4 (#47616)
      • 1bcf3b6
        1bcf3b6[ggml] Update, backport vulkan loader patch, restore test integrity (#47495)
      • 6548e2e
        6548e2e[ggml, llama-cpp] update to 0.9.1, 6550 (#47464)
      • 6c50343
        6c50343[ggml,llama-cpp,whisper-cpp] Fix exported config, add test ports (#45745)
      • 0aab0c9
        0aab0c9[ggml,llama-cpp] Update (#47112)
      • 507dfce
        507dfce[ggml,llama-cpp,whisper-cpp] Update, features, cleanup (#46569)
      • 7e7032a
        7e7032a[ggml,llama-cpp,whisper-cpp] Revise, fix features (#45756)
      • cf72b50
        cf72b50[llama-cpp] add new port (and its ggml dependency) (#43925)

      #Port Files