intel
★ 2,707neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
HYSEN LABS DIRECTORY
intel
Verified repositories, classifications and analysis from the intel organization.
2 curated open-source projects
intel
★ 1,614auto-round
Intel AutoRound is a model optimization toolkit for quantization workflows that lowers inference cost while preserving accuracy for AI deployment.