yuyang comments

Results 9 comments of


                                            yuyang

模型量化后运行时间比不量化更长，感觉是负优化

方便的话，原始模型和量化模型邮件一下，我们测试看看。

operation requirements

Please specify where the op comes from(Tensorflow, Caffe, or ONNX) like this: - Not Supported OP: ... - Framework ...

operation requirements

> Sorry, my meaning is ShuffleChannel. ShuffleChannel is NOT a OP in pytorch、onnx or tensorflow! By the way tensorflow-shufflenet is tested. You can try.

Pytorch3D install error

PlanB: git checkout 5e7707b

issue about the exported onnx model

By the way, the AIMET commit: 35e588226f02 with torch-gpu.

issue about the exported onnx model

QNN version：2.16.4.231110

issue about the exported onnx model

Thank you for your reply. I met the same issue with QNN latest version 2.17.0.231124.

issue about the exported onnx model

> Thanks for sharing your QNN version. I was under the impression that this issue is resolved with QNN version you are using. But let me check and get back...

Does llama2 example on Android utilize HTP?

> > We can run smaller version of Llama structure in HTP, and WIP for the 7B and 8B models in HTP. cc @cccclai. Running Llama in mobile GPU is...