smoothquant， any quant/dequant module can be found in exported quant pt model ?

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

2.23k stars 257 forks source link

Closed tianylijun closed 2 months ago

tianylijun commented 2 months ago

intel/neural-compressor/examples/3.x_api/pytorch/nlp/huggingface_models/language-modeling/quantization/smooth_quant/run_clm_no_trainer.py

问下，导出的量化模型里面，有没有QDQ节点？