Maksim Proshin comments

Results 47 comments of


                                            Maksim Proshin

[Fixed]: Issues resolved raised by mypy for issue Make #22313

@AtharvaPore01 , do you plan to continue to work on this PR?

[PTQ] Add support of arbitrary batch size for PTQ

@kshpv , please also update the documentation accordingly

ERROR : While Quantization of OpenVINO model

Dear @ashish-2005 , All the mentioned above fixes have been merged to recent NNCF 2.5.0 release. Have you tried it? Is your problem still valid?

DataParallel crashes about "not same cuda device" when training after onnx export

@ljaljushkin , @vshampor , is it still valid?

Different model output after compression in NNCFNetwork and .onnx/.xml

@korotaS , as I see from your last comment, you were able to solve the accuracy problem. Do you have any objections if we close this issue?

model architecture with unexpected changes after pruning

I close this issue as there is no feedback from the user for a long time period. Feel free to create a new issue, if it's still valid.

Mypy checks for NNCF common pruning code

@daniil-lyakhov @RitikaxShakya what is the status of this PR? Is it still active?

Add information about the integration with sentence-transformers

see also https://www.linkedin.com/posts/tomaarsen_sentence-transformers-v330-introduced-int8-activity-7262116975928135681-yUcE?utm_source=share&utm_medium=member_desktop

DeformConv2d Cannot be Quantized

@AlexanderDokuchaev @anzr299 what's the status of this issue? Is it still valid?

The question about function create_compressed_model()：RuntimeError: CUDA error: device-side assert triggered

@zbnlala , do you have any feedback?