quantization

Modules

modelopt.onnx.quantization.autotune	Pattern-Based Q/DQ Autotuning for ONNX Models.
modelopt.onnx.quantization.calib_utils	Provides basic calibration utils.
modelopt.onnx.quantization.extensions	Module to load C++ extensions.
modelopt.onnx.quantization.fp8	Performs FP8 GEMM only quantization of an ONNX model, and returns the ONNX ModelProto.
modelopt.onnx.quantization.graph_indexing	Graph indexing and pattern matching for ONNX quantization.
modelopt.onnx.quantization.graph_rewrites	Shared ONNX graph rewrites for quantization.
modelopt.onnx.quantization.graph_selection	Node selection and runtime probes for calibrated ONNX quantization.
modelopt.onnx.quantization.gs_patching	Patches onnx_graphsurgeon to support explicitly setting a dtype.
modelopt.onnx.quantization.int4	Performs INT4 WoQ on an ONNX model, and returns the ONNX ModelProto.
modelopt.onnx.quantization.int8	Performs INT8 quantization of an ONNX model, and returns the ONNX ModelProto.
modelopt.onnx.quantization.operators	Additional or modified QDQ operators on top of ORT quantized operators.
modelopt.onnx.quantization.ort_patching	This module contains all the patched functions from ORT.
modelopt.onnx.quantization.ort_utils	Provides basic ORT inference utils, should be replaced by modelopt.torch.ort_client.
modelopt.onnx.quantization.partitioning	Utilities related to partitioning the ONNX model to place QDQ nodes.
modelopt.onnx.quantization.precision_utils	Shared runtime-precision conversion for ONNX quantization.
modelopt.onnx.quantization.qdq_graph	Q/DQ graph policy for ONNX quantization.
modelopt.onnx.quantization.qdq_utils	Various utils to support inserting Q/DQ nodes.
modelopt.onnx.quantization.quant_utils	Provides some basic utilities that can be used in quantize() methods.
modelopt.onnx.quantization.quantize(onnx_path)	Quantizes the provided ONNX model.

Model optimization subpackage for onnx quantization.