intel / neural-compressor

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
https://intel.github.io/neural-compressor/
Apache License 2.0
2.18k stars 252 forks source link

Complement UT of calibration function for TF 3x API #1945

Closed zehao-intel closed 2 months ago

zehao-intel commented 2 months ago

Type of Change

UT

Description

complement UT of calibration function for TF 3x API

How has this PR been tested?

PreCI

Dependency Change?

No