dongxiao

Hi, I want to know how nnpack implement the kernels used in convolution inference. By reading the codes, I find the computation is taken by kernels in src/x86_64. For examples,...

[QST] how to undersrtand a cutlass kernel name?

2

**What is your question?** I'd like to understand if we could recognize which tensor core instruction and what's the data types for a given cutlass kernel. For example, for kernel...

Could I get pruned models on CIFAR10

2

Thanks for your impressive work.I'd like to know if I could find the pruned resnet model on CIFAR10.As I know, only models for imagenet are released now. Thank you!

I installed Caffe-HRT as the installation guide. I want to measure the performace on cpu under single thread. I use top -H to monintor the threads used in Caffe-HRT and...

sparse resnet model

1

### Issue summary I'd like to use the sparse resnet model. I have downloaded the model from "SkimCaffe/models/resnet/ResNet-50-model.caffemodel.bz2" and loaded it using caffe c++ interface. But when iterating the entry...

I hit one issue when running inference.py with Billa7B-SFT. It runs well on languague model vicuna7B while I hit this erorr when the languague model gets changed to Billa7B-SFT. Here...

should we set use_global_stats to true during test?

1

Thanks for your codes! I have a problem about the configuration in batchnorm layer. Under my understanding,batchnorm layer should use moving average of mean and variance computed during training phase.So...

trained model for dataset dgs

1

Hi, Thanks for open-sourcing your code. I find the trained models are provided for dataset phoenix and csldaily. But I cannot find the trained model for DGS3-T. I want to...