AI People Wiki

Builders & open source

Radoslav Gerganov

Code owner for the RPC backend (ggml-org/ggml-rpc), llama.cpp project

  • Code owner for the RPC backend (ggml-org/ggml-rpc), llama.cpp project13

Radoslav Gerganov is the code owner for llama.cpp's RPC backend, according to the project's CODEOWNERS file, which lists Gerganov as the sole member of the ggml-rpc team covering the backend and its server tool. The project's documentation says the RPC server exposes ggml devices on a remote host and that the RPC backend offloads computations to one or several of those servers. Gerganov's commits add multi-device support, compute-graph caching and reuse, a refactored transport, and asynchronous backend APIs to the RPC backend, along with request-handling changes in llama-server.123

At a glance

Current role
Code owner for the RPC backend (ggml-org/ggml-rpc)
Sector
Independent
Work listed
2
Sources cited
11
Profile reviewed

Open-source work

Radoslav Gerganov authored the pull request that added the RPC backend to ggml and llama.cpp, merged in May 2024; its commit message describes a backend that proxies all operations to a remote server running a regular CPU, CUDA or Metal backend. Follow-up pull requests by Gerganov added RPC support to llama-server and SYCL support to rpc-server.456

The project's CODEOWNERS file lists Gerganov as the sole member of the ggml-org/ggml-rpc team, which owns the backend source and the tools/rpc server. Gerganov's commits since September 2025 add multi-device support, compute-graph caching and reuse, a transport refactor and asynchronous backend APIs. A March 2023 commit by Gerganov added a README section on running the project on Android.1327

Writing and reverse engineering

Gerganov's blog, subtitled "random hacks," covers reverse engineering and hardware hacking. Posts include a 2021 look at how SoftHSMv2, a software PKCS#11 implementation, persists its state, a 2023 write-up of Shanocast, and 2025 posts on reverse engineering the MAGic Remote set-top-box protocol to build an open-source client and on weak algorithms routers use to generate default Wi-Fi passwords.8910

Work and contributions

  • llama.cpp RPC backend Open-source code

    CODEOWNERS lists Gerganov as the ggml-org/ggml-rpc team, which owns ggml/src/ggml-rpc and tools/rpc; a September 2025 commit added Gerganov as RPC owner. Commits authored from September 2025 to August 2026 add multi-device support, graph caching and reuse, a transport refactor, and event and async backend APIs, plus llama-server changes such as returning HTTP 400 when a prompt exceeds the context length. The repository is MIT-licensed.13211

  • Shanocast Open-source code

    Wrote this Chromecast receiver for Linux, built on the open-source Openscreen implementation of the Chromecast protocol, which can mirror a Chrome tab or the whole desktop.9

Timeline

  1. Committed a llama.cpp README section on running the project on Android.7
  2. Published Shanocast, a Chromecast receiver for Linux.9
  3. Gerganov's pull request adding the RPC backend to ggml and llama.cpp, which proxies operations to remote servers, was merged.4
  4. Added support for the RPC backend to llama-server.5
  5. Added SYCL backend support to the llama.cpp rpc-server.6
  6. Published a reverse-engineering write-up of the MAGic Remote protocol with an open-source client.10
  7. Was added to CODEOWNERS as owner of the llama.cpp RPC backend.13

Where they work

Suggest a correction or removal

Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.

References

11 sources · profile reviewed Oct 21, 2026 · data updated Oct 21, 2026

  1. ggml-org/llama.cpp CODEOWNERSggml-org (GitHub repository) · Repository · accessed Oct 21, 2026
  2. llama.cpp tools/rpc READMEggml-org (GitHub repository) · Documentation · accessed Oct 21, 2026
  3. ggml-org/llama.cpp commits authored by rgerganovggml-org (GitHub repository) · Repository · accessed Oct 21, 2026
  4. ggml : add RPC backend — ggml-org/llama.cpp pull request #6829ggml-org (GitHub repository) · Repository · published May 14, 2024 · accessed Oct 21, 2026
  5. server : add support for the RPC backend — ggml-org/llama.cpp pull request #7305ggml-org (GitHub repository) · Repository · published May 17, 2024 · accessed Oct 21, 2026
  6. rpc-server : add support for the SYCL backend — ggml-org/llama.cpp pull request #10934ggml-org (GitHub repository) · Repository · published Dec 23, 2024 · accessed Oct 21, 2026
  7. ggml-org/llama.cpp commit 60f819a: Add section to README on how to run the project on Android (#130)ggml-org (GitHub repository) · Repository · published Mar 14, 2023 · accessed Oct 21, 2026
  8. random hacks — Radoslav Gerganov's blogRadoslav Gerganov · Official page · accessed Oct 21, 2026
  9. Making a Chromecast receiver (Project Shanocast)Radoslav Gerganov · Official page · published Sep 27, 2023 · accessed Oct 21, 2026
  10. Reversing MAGic RemoteRadoslav Gerganov · Official page · published Jan 19, 2025 · accessed Oct 21, 2026
  11. ggml-org/llama.cpp LICENSE (MIT)ggml-org (GitHub repository) · License · accessed Oct 21, 2026