<br />

<button value="stable" default="">See Stable</button> <button value="nightly">See Nightly</button>

<br />

DO NOT EDIT.

This file was autogenerated. Do not edit it by hand,
since your modifications would be overwritten.

## Classes

[`class AWQConfig`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/AWQConfig): Configuration class for AWQ (Activation-aware Weight Quantization).

[`class AbsMaxQuantizer`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/AbsMaxQuantizer)

[`class Float8QuantizationConfig`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/Float8QuantizationConfig): FP8 quantization config.

[`class GPTQConfig`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/GPTQConfig): Configuration class for the GPTQ (Gradient-based Post-Training Quantization) algorithm.

[`class Int4QuantizationConfig`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/Int4QuantizationConfig): Int4 quantization config.

[`class Int8QuantizationConfig`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/Int8QuantizationConfig): Int8 quantization config.

[`class QuantizationConfig`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/QuantizationConfig): Base class for quantization configs.

[`class Quantizer`](https://www.tensorflow.org/api_docs/python/tf/keras/Quantizer)

## Functions

[`abs_max_quantize(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/abs_max_quantize): Quantizes the input tensor using the absolute maximum quantization scheme.

[`abs_max_quantize_grouped_with_zero_point(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/abs_max_quantize_grouped_with_zero_point): Quantizes a 2D tensor using grouped asymmetric quantization with zero point.

[`compute_float8_amax_history(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/compute_float8_amax_history)

[`compute_float8_scale(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/compute_float8_scale)

[`deserialize(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/deserialize): Return a Keras quantizer object via its config.

[`fake_quant_with_min_max_vars(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/fake_quant_with_min_max_vars): Perform per-tensor or per-channel fake quantization.

[`get(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/get): Retrieve a Keras quantizer object via an identifier.

[`pack_int4(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/pack_int4): Pack an int4 tensor into an int8 tensor with packed nibbles.

[`quantize_and_dequantize(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/quantize_and_dequantize)

[`serialize(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/serialize)

[`unpack_int4(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/quantizers/unpack_int4): Unpack a packed int4 back to an int8 tensor in the range \[-8, 7\].