Independent project. Not a U.S. government website.

Support our project (opens Buy Me a Coffee)
USASI

Piotr Wilkin

Maintains llama.cpp's parser code and contributes to Lemonade; systems architect at Syndatis

  • Systems architect, Syndatis1
  • Parser code maintainer; code owner for tools/parser and the chat tests, llama.cpp project12

Piotr Wilkin, who also uses the handle ilintar, describes Wilkin's work on GitHub as programmer and systems architect at Syndatis, maintainer of llama.cpp's parser code, contributor to Lemonade, and author of trellis.cpp. llama.cpp's CODEOWNERS file names Wilkin as owner of the parser tool and the chat tests, co-owner of the debug example, and a member of the shared-code (llama-common) team; Wilkin's commits there cover chat-template parsing and tool calls, support for new models, and CUDA and Vulkan kernels. In Lemonade, an AMD-sponsored local AI server, Wilkin's 2026 commits add asset- and audio-generation backends and a job engine, and fix its llama.cpp integration.12356

Work

  • llama.cppOpen-source code

    CODEOWNERS names Wilkin for tools/parser and tests/test-chat, co-owner (with Daniel Bevenius) of examples/debug, and a member of the ggml-org/llama-common team. Commits authored from June to October 2026 split specialized chat parsers into common/parsers, fix DeepSeek and other chat templates and tool calls, add model support such as Kimi-K3, and tune CUDA, HIP and Vulkan kernels. The repository is MIT-licensed.234

    Project page (external site: github.com)

  • LemonadeOpen-source code

    Commits authored from July to September 2026 add asset generation (Trellis and OpenMOSS), audio generation backends (ThinkSound and ACE-Step) and a job engine, and fix how Lemonade finds and launches llama.cpp. The repository is Apache-2.0 licensed and states that the project is sponsored by AMD.56

    Project page (external site: github.com)

This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.

Sources · reviewed Oct 13, 2026

  1. 1.
    pwilkin (Piotr Wilkin) on GitHub (external site: github.com)

    GitHub · Official page · accessed Oct 13, 2026

  2. 2.
    ggml-org/llama.cpp CODEOWNERS (external site: github.com)

    ggml-org (GitHub repository) · Repository · accessed Oct 13, 2026

  3. 3.
    ggml-org/llama.cpp commits authored by pwilkin (external site: github.com)

    ggml-org (GitHub repository) · Repository · accessed Oct 13, 2026

  4. 4.
    ggml-org/llama.cpp LICENSE (MIT) (external site: github.com)

    ggml-org (GitHub repository) · License · accessed Oct 13, 2026

  5. 5.
    lemonade-sdk/lemonade commits authored by pwilkin (external site: github.com)

    lemonade-sdk (GitHub repository) · Repository · accessed Oct 13, 2026

  6. 6.
    lemonade-sdk/lemonade README (sponsorship and Apache-2.0 license) (external site: github.com)

    lemonade-sdk (GitHub repository) · Repository · accessed Oct 13, 2026

Support Us

Help keep USASI useful.

Optional. No USASI account required. Payment takes place on the linked provider’s website (Buy Me a Coffee).

About supporting this project