Popular repositories Loading

1. apex-quant apex-quant Public

   Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization

   Shell 363 26

2. privacy-filter.cpp privacy-filter.cpp Public

   OpenAI's privacy filter NER model architecture implemented in a minimal C++/GGML runtime

   C++ 264 13

3. LocalVQE LocalVQE Public

   Lean neural real-time acoustic echo cancellation with soft delay estimation - GGML and PyTorch inference

   C++ 160 17

4. vibevoice.cpp vibevoice.cpp Public

   C++ port of Microsoft VibeVoice built on ggml

   C++ 106 11

5. rf-detr.cpp rf-detr.cpp Public

   rt-detr implementation in C++ with ggml

   C++ 19 2

6. localai-realtime-demo localai-realtime-demo Public

   Go 10