Open source repositories tagged with #nvfp4, ranked by health score.
A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包
cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.
Native Windows port of NInfer engine for RTX 5090. Features Qwen3.8-27B with QUASAR and NInfer models, MTP/DFlash2 with vision and 262,144 context
