QUInt4x2Storage

Storage for quantized 4x2 int8 tensors.

Abstract Signature:

QUInt4x2Storage(args)

PyTorchJAX (Core)NumPyKerasTensorFlowApple MLXFlax NNXPaxML / Praxis

PyTorch

API: torch.QUInt4x2Storage

Strategy: Direct Mapping

Official Docs ↗

JAX (Core)

API: —

Strategy: Custom / Partial

NumPy

API: —

Strategy: Custom / Partial

Keras

API: —

Strategy: Custom / Partial

TensorFlow

API: —

Strategy: Custom / Partial

Apple MLX

API: —

Strategy: Custom / Partial

Flax NNX

API: —

Strategy: Custom / Partial

PaxML / Praxis

API: —

Strategy: Custom / Partial