Pablo Gonzalez

Results 45 comments of Pablo Gonzalez

Not relevant anymore, closing issue

Ideally this test can be applicable to: `rnnt`, `bert`, `dlrm`, `retinanet`

@arjunsuresh I am not sure, I see there is another conf file [here](https://github.com/mlcommons/inference/blob/master/language/gpt-j/mlperf.conf) that also doesn’t have the gpt-j details. @badhri-intel @rnaidu02 Do you know if we need to put...

@pgmpablo157321 - Add option in submission checker to remove all the stable diffusion images folder, and skip the checks done for the images folder - Remove the images from the...

![Stdev_olympic_prunning](https://github.com/user-attachments/assets/f675687c-393f-44c4-b036-feb0006fe652)

![RCPs_pruned_varying_Stdev](https://github.com/user-attachments/assets/8ac22754-7223-4fbf-a35e-9b38cf70dc2a)

@ShriyaPalsamudram I am getting the same results when with and without the olympic stdev. It seems to be, because it the `RCP Stdev` is only being used to compute the...

![RCPs_MaxSpeedUP](https://github.com/user-attachments/assets/d88fd159-2328-4238-aaea-fc639164f1b0)

Additionally, an example of the max_speed_up values for last training results: **HPE-Cray-XD670-Gen11-H100-SXM5-80GB_n1_mxnet_24.04** With olympic score: ``` [1.018748075108887, 1.0601459916687128] ``` Without olympic score: ``` [1.0262860923600325, 1.0699036853548622] ```

@nvzhihanj @hanyunfan I opened a PR with the changes needed for this. No LoadGen changes were needed for this change, we are just adding a scenario in the submission checker...