↔ [Converter] Add support for aten.gelu and aten.tanh in the FX aten path

[gs-olive]

aten.gelu + aten.tanh

• Function Schema: torch.ops.aten.gelu.default: ((torch.float32,), {}), torch.ops.aten.tanh.default: ((torch.float32,), {})

• Original PyTorch API: torch.gelu, torch.tanh

• Relevant TensorRT Documentation: IActivationLayer

  • Potentially can take inspiration from existing TorchScript GeLU lowering pass

Add support for gelu and tanh as aten converters.

[github-actions]

This issue has not seen activity for 90 days, Remove stale label or comment or this will be closed in 10 days