Sathyaprakash Narayanan

Channel Sorting

2

@VainF As a feature request. Would it be possible to apply channel sorting based on channels? If you can provide any insights it would be really helpful. # function to...

Fails Pruning on Mobilenet v2 and v3

1

I'm trying to apply Channelwise Pruning. There persists few issues, 1. However, a few layers were not able to be pruned; the list of layers is printed out via the...

Bug: Porting model another device (CPU/GPU)

4

* snntorch version: 0.7.0 * Python version: 3.10.13 * Operating System: Ubuntu x64 ### Description When I load a pre-trained model and push it from GPU->CPU or the vice versa....

`summary(model.to(device),(3,640,640), dtypes= [torch.half])` returns > summary() got an unexpected keyword argument 'dtypes'

node operation torch_nn_modules_conv_Conv2d_conv1_1

7

I'm trying to convert a simple model from onnx2c. I have attached the architecture here:  Upon compilation, I get ` [Fatal] (createNode) Unimplemented: node operation torch_nn_modules_conv_Conv2d_conv1_1` What am I...

Any thoughts or suggestions would be appreciated. Thanks in advance.

AWQ for non-Transfomer Implementation

3

I found the work to be really interesting, I'm trying to replicate the work for non-transformer architectures like CNN's. Any suggestions on how to proceed would be appreciated. Thanks in...

How should one go about using it on a non-transformer layer? Any suggestions would be helpful. Thanks in advance.

In the function `_search_module_scale`. https://github.com/mit-han-lab/llm-awq/blob/79019832efd37e4c24a695442880190858aa605e/awq/quantize/auto_scale.py#L131 ) ``` for fc in linears2scale: fc.weight.mul_(scales.view(1, -1).to(fc.weight.device)) fc.weight.data = w_quantize_func(fc.weight.data) / (scales.view(1, -1)) ``` The FC weights are updated for each scale used in...