ONNX Quantization

Creator

Creator

Seonglae Cho

Created

Created

2023 Jun 1 14:13

Editor

Editor

Seonglae Cho

Edited

Edited

2023 Sep 13 8:16

Refs

Refs

Model Quantization

32bit floating point to 8bit linear quantization

ONNX Quantization Notion

ONNX quantization pre-processing

Asymmetric quantization

Symmetric quantization

Dynamic Quantization

Static Quantization

ONNX Quantization Usages

Quantization on GPU

Quantize ONNX models

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

https://onnxruntime.ai/docs/performance/model-optimizations/quantization.html

Quantize ONNX models

Backlinks

HuggingFace Optimum ONNX

Recommendations

///////