ggml

{
  "aliases": [],
  "alternatives": [
    "TensorFlow",
    "PyTorch",
    "ONNX Runtime",
    "ncnn"
  ],
  "build_dependencies": [
    "cmake"
  ],
  "categories": [
    "library",
    "machine-learning",
    "math"
  ],
  "caveats": null,
  "conflicts_with": [],
  "dependencies": [
    "libomp"
  ],
  "deprecated": 0,
  "deprecation_reason": null,
  "desc": "Tensor library for machine learning",
  "disable_reason": null,
  "disabled": 0,
  "enrichment_fetched_at": "2026-06-20T23:38:00+00:00",
  "first_seen": "2026-06-20T23:34:18+00:00",
  "full_name": "ggml",
  "github_default_branch": "master",
  "github_last_commit_at": "2026-06-19T07:14:44Z",
  "github_readme_excerpt": "# ggml\n\n[Manifesto](https://github.com/ggerganov/llama.cpp/discussions/205)\n\nTensor library for machine learning\n\n***Note that this project is under active development. \\\nSome of the development is currently happening in the [llama.cpp](https://github.com/ggerganov/llama.cpp) and [whisper.cpp](https://github.com/ggerganov/whisper.cpp) repos***\n\n## Features\n\n- Low-level cross-platform implementation\n- Integer quantization support\n- Broad hardware support\n- Automatic differentiation\n- ADAM and L-BFGS optimizers\n- No third-party dependencies\n- Zero memory allocations during runtime\n\n## Build\n\n```bash\ngit clone https://github.com/ggml-org/ggml\ncd ggml\n\n# install python dependencies in a virtual environment\npython3.10 -m venv .venv\nsource .venv/bin/activate\npip install -r requirements.txt\n\n# build the examples\nmkdir build \u0026\u0026 cd build\ncmake ..\ncmake --build . --config Release -j 8\n```\n\n## GPT inference (example)\n\n```bash\n# run the GPT-2 small 117M model\n../examples/gpt-2/download-ggml-model.sh 117M\n./bin/gpt-2-backend -m models/gpt-2-117M/ggml-model.bin -p \"This is an example\"\n```\n\nFor more information, checkout the corresponding programs in the [examples](examples) folder.\n\n## Resources\n\n- [Introduction to ggml](https://huggingface.co/blog/introduction-to-ggml)\n- [The GGUF file format](https://github.com/ggerganov/ggml/blob/master/docs/gguf.md)\n",
  "github_repo": "ggml-org/ggml",
  "github_stars": 14849,
  "github_topics": [
    "automatic-differentiation",
    "large-language-models",
    "machine-learning",
    "tensor-algebra"
  ],
  "homepage": "https://github.com/ggml-org/ggml",
  "homepage_og_description": null,
  "homepage_og_image": null,
  "homepage_title": null,
  "installs_30d": 29329,
  "installs_365d": 72414,
  "installs_90d": 69436,
  "keg_only": 0,
  "keg_only_reason": null,
  "last_seen": "2026-06-20T23:34:18+00:00",
  "license": "MIT",
  "llm_generated_at": "2026-06-20T23:43:17+00:00",
  "llm_model": "claude-haiku-4-5",
  "name": "ggml",
  "oldnames": [],
  "one_liner": "C tensor library with quantization, automatic differentiation, and broad hardware support for machine learning workloads.",
  "optional_dependencies": [],
  "rank_30d": 191,
  "rank_365d": 532,
  "rank_90d": 225,
  "raw_hash": "1b269cbbab73c423",
  "recommended_dependencies": [],
  "revision": 0,
  "ruby_source_path": "Formula/g/ggml.rb",
  "tap": "homebrew/core",
  "test_dependencies": [
    "cmake"
  ],
  "uses_from_macos": [],
  "version_head": "HEAD",
  "version_stable": "0.15.2",
  "versioned_formulae": [],
  "why_use_this": "ggml is the foundational library powering llama.cpp and whisper.cpp, enabling efficient inference of large language and speech models on consumer hardware. It excels at integer quantization for memory-efficient deployment and requires no external dependencies, making it ideal for embedding ML capabilities in C/C++ applications without heavy frameworks."
}