Hansong Zhang

Hi @adonnini > I tried running setup.sh from both the LlamaDemo and ExecutorchDemo directories. They both failed. Please run from root directory. For prebuilt AAR, maybe use [this 0.5 release](https://ossci-android.s3.amazonaws.com/executorch/release/v0.5.0-rc3/executorch.aar)?...

Hi @adonnini Let's confirm the SHA of executorch.aar is b778e651f614ed33581d51da43d554515f84dd74 executorch.aar Also I have the following deps in build.gradle.kts ``` implementation(files("libs/executorch.aar")) implementation("com.facebook.soloader:soloader:0.10.5") implementation("com.facebook.fbjni:fbjni:0.5.1") ```

Hi @adonnini Thank you for your updates! Sorry would you mind using https://github.com/pytorch/executorch/tree/main/extension/benchmark/android/benchmark as an example, instead of ExecuTorchDemo? I used `includeBuild("../../../../extension/android")` in the past and didn't have a chance...

> No Cannot resolve method 'toTensor' in 'EValue' error. I probably saw this kind of error from android studio in the past but I can finally compile. Is it android...

> Is there a release newer than v0.5.0-rc3? 0.6 not yet available.

Hi @adonnini `forward()` returns `EValue[]` so most likely you want `mModule.forward(EValue.from(arrDataPytorch))[0].toTensor();` However, seems that `forward` didn't run successfully. Error is `InvalidArgument = 0x12`

May I ask what kind of model and input did you use?

Seems that your input is a tensor right? May I ask what is inside arrDataPytorch?

for `tmpData` dimensions: {neuralNetworkUserLocationsInsideEstimationRadius.size(), 6} do you need the last 1 dimension in `shapeArrDataPytorchFlattened = new long[]{tmpData.length, 6, 1};` ? Does the model need a 3-D input?

Also, let's do a really fast sanity check, what about you use `forward()` without argument? (will be filled with ones implicitly) ``` outputTensor = mModule.forward()[0].toTensor(); //EXECUTORCH ```