Wrong import in inference quantization example
Hi,
At https://github.com/microsoft/DeepSpeedExamples/blob/master/inference/huggingface/zero_inference/README.md , the referenced import from deepspeed.compression.inference.quantization import _init_group_wise_weight_quantization is wrong.
The correct one is from deepspeed.inference.quantization import _init_group_wise_weight_quantization .
Can you please correct it? Best regards, Epliz
I get this error using from deepspeed.compression.inference.quantization import _init_group_wise_weight_quantization :
ModuleNotFoundError: No module named 'deepspeed.compression.inference'
And this with 'from deepspeed.inference.quantization import _init_group_wise_weight_quantization':
File "/home/sw/bulldozer/code/deepspeed/DeepSpeedExamples/inference/huggingface/zero_inference/deep.py", line 1, in <module> from deepspeed.inference.quantization import _init_group_wise_weight_quantization ImportError: cannot import name '_init_group_wise_weight_quantization' from 'deepspeed.inference.quantization' (/home/sw/anaconda3/envs/deepseed/lib/python3.10/site-packages/deepspeed/inference/quantization/__init__.py)