Model-to-NPU pipelines for Qualcomm Snapdragon: QNN/ONNX/Android runtimes for on-device image and video generation.
Claude Code skills for Qualcomm QAIRT/QNN model deployment — ONNX to Hexagon HTP, AIMET quantization, eSDK cross-compilation
Snapdragon X Elite (Hexagon NPU) LLM: Genie server exposing Anthropic + OpenAI APIs for on-device inference
llama.cpp fork with an experimental QNN backend for the Hexagon NPU on Windows on Snapdragon
Keyboard-driven .NET terminal UI to find, run, chat with, and serve GGUF/LLM models on the Qualcomm Snapdragon NPU via GenieX — with auto CPU/NPU/GPU compute selection and one-key offload to external/NAS drives.
GPT-SoVITS v2Pro on Qualcomm QCS8550 NPU (QNN/HTP, fp16): conversion pipeline from GPT-SoVITS training logs, numpy + QNN runtime, OpenAI-compatible TTS service
To associate your repository with the qairt topic, visit your repo's landing page and select "manage topics."