Neural Compressor

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

LLM OrchestrationOpen Source AI & Machine LearningOpen Source

Usi Neural Compressor?

Tieni traccia del suo costo insieme al resto del tuo stack e ricevi un promemoria prima del rinnovo.

Aggiungi al mio stack

Vendor

Intel

Publisher of Intel OpenVINO

View vendor profile

More by Intel