aimet-onnx 1.35.0 installation command is broken - wheel name changed from cu117 to cu118

[EchoLynx]

Running the aimet-onnx GPU installation command from the installation documentation produces the following error:

$ python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.0/aimet_onnx-1.35.0.cu117-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Looking in links: https://download.pytorch.org/whl/torch_stable.html
Collecting aimet-onnx==1.35.0.cu117
  ERROR: HTTP error 404 while getting https://github.com/quic/aimet/releases/download/1.35.0/aimet_onnx-1.35.0.cu117-cp310-cp310-manylinux_2_34_x86_64.whl
ERROR: Could not install requirement aimet-onnx==1.35.0.cu117 from https://github.com/quic/aimet/releases/download/1.35.0/aimet_onnx-1.35.0.cu117-cp310-cp310-manylinux_2_34_x86_64.whl because of HTTP error 404 Client Error: Not Found for url: https://github.com/quic/aimet/releases/download/1.35.0/aimet_onnx-1.35.0.cu117-cp310-cp310-manylinux_2_34_x86_64.whl for URL https://github.com/quic/aimet/releases/download/1.35.0/aimet_onnx-1.35.0.cu117-cp310-cp310-manylinux_2_34_x86_64.whl

It looks like the documentation hasn't kept up with a change in the wheel name, which seems to represent a change from using CUDA 11.7 (cu117) to CUDA 11.8 (cu118).

On the release page for AIMET 1.35.0, you can see that the aimet-onnx whl file for GPU now uses cu118 instead of cu117. Interestingly, the release notes still say cu117.

Returning to the installation documentation, you can see that cu117 is still used for the wheel name, and that's what's causing the 404 error.