#144 · Primary category： Inference & Local Deploy
llamacpp-rocm
Fresh builds of llama.cpp with AMD ROCm™ 7 acceleration
Project last updated：08/29/26
GitHub Stars
698
Forks
72
Contributors
6
License
MIT
Why we included this project
Compiling llama.cpp for AMD GPUs is a known chore: you have to match the build to your exact card and get ROCm set up just right. This project removes that step by shipping nightly llama.cpp builds with the ROCm 7 runtime already bundled, so you grab an archive for your GPU target and run llama-server straight away. The build matrix covers a wide range of AMD hardware, from RDNA2, RDNA3, and RDNA4 discrete cards to the Strix Halo and Strix Point APUs and Instinct accelerators, on both Windows and Ubuntu. It is a practical shortcut for anyone who wants current llama.cpp features on AMD silicon without wrestling the toolchain, and it slots in well with Lemonade and similar local-inference apps. One caveat: the project is focused on its own production context and does not offer comprehensive support, so treat it as a convenient distribution rather than a supported platform.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
llama.cpp
LLM inference in C/C++
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.