QuantizePerChannel

Converts a float tensor to a per-channel quantized tensor with given scales and zero points.

Abstract Signature:

QuantizePerChannel(input: Tensor, scales: Tensor, zero_points: Tensor, axis: int, dtype)

PyTorchJAX (Core)KerasTensorFlowApple MLXFlax NNXPaxML / Praxis

PyTorch

API: torch.quantize_per_channel

Strategy: Direct Mapping

Official Docs ↗

JAX (Core)

API: —

Strategy: Custom / Partial

Keras

API: —

Strategy: Custom / Partial

TensorFlow

API: tf.quantization.quantize_and_dequantize_v2

Strategy: Direct Mapping

Official Docs ↗

Apple MLX

API: —

Strategy: Custom / Partial

Flax NNX

API: —

Strategy: Custom / Partial

PaxML / Praxis

API: —

Strategy: Custom / Partial