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

¿Usas Neural Compressor?

Controla su coste junto al resto de tu stack y recibe un recordatorio antes de que se renueve.

Añadir a mi stack

Vendor

Intel

Publisher of Intel OpenVINO

View vendor profile

More by Intel