e-said

Results 21 comments of e-said

Hello @jianbin-zhang, Your link is pointing to the "latest" AIMET version, which is not 1.31.0. Please follow [this link](https://quic.github.io/aimet-pages/releases/1.31.0/install/install_host.html) for AIMET 1.31.0. Based on the error message, it appears that...

I've seen the updates on packages section, Thanks @quic-akhobare

Hi @quic-bharathr, Thanks for the information. I noticed that during the [installation of common Debian packages](https://quic.github.io/aimet-pages/releases/1.32.0/install/install_host.html) for Pytorch, the following path is missing: _/usr/local/lib/python3.10/dist-packages/aimet_torch/bin/reqs_deb_torch_common.txt_ I was able to create the...

Hi @Jamil, The model preparer issue is related to Torch FX tracing. To resolve this, you'll need to modify your code to ensure that the model is traceable by Torch...

Hello The installation instructions have changed slightly. Did you check the latest [doc](https://quic.github.io/aimet-pages/releases/1.32.0/install/install_host.html)?

I successfully imported the library you mentioned without any issues. I'm installing AIMET on top of a custom docker image. If it helps, you can find below the shell script...

Hi @escorciav, Could you check my last reply on [this ticket](https://github.com/quic/aimet/issues/3147) ? that will probably help on fixing your issue

Adding those lines after aimet-wheels installation should fix your issue: # Install common debian packages: cat /usr/local/lib/python3.10/dist-packages/aimet_torch/bin/reqs_deb_common.txt | xargs apt-get --assume-yes install cat /usr/local/lib/python3.10/dist-packages/aimet_torch/bin/reqs_deb_torch_gpu.txt | xargs apt-get --assume-yes install ln...

> or should I point to the files in the conda env? Ah yes you are right, you should point to conda in your case. > Are you using Docker?...

Hello @bhushan23 I'm an Embedded AI instructor designing a hands-on lab session for my students to explore model quantization. I plan to use AIMET as the primary tool for this...