FastFlowLM is an open-source runtime for running large language models on AMD XDNA 2 NPUs under Linux. It enables efficient, low-power local inference for LLMs and Whisper, targeting developers and researchers with compatible hardware.
FastFlowLM is an Other AI product. It focuses on running large language models efficiently on AMD NPUs for local inference on Linux systems. FastFlowLM is an open-source project aimed at developers and researchers using AMD NPU-equipped Linux systems. The project is open source (MIT). FastFlowLM is available on the command line and Linux, and it can be self-hosted.
Lemonade and FastFlowLM contributors builds and maintains FastFlowLM, and the product first shipped in 2025. The project is developed in the open on GitHub with 1.5k stars and 216 commits in the last 90 days. Across PulseGate's embedding index, FastFlowLM has few near neighbours, marking it as relatively distinct. Among its 5 catalogued features are NPU support, local inference, and linux compatibility.
Latest indexed changes and source events
lemonade-server.ai discovered by the PulseGate indexer
Other apps tracked under the same category.
