[vulkan] Allow benchmark binary to handle non-single tensor inputs/outputs for Vulkan models (#73109)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/73109
This change updates the Vulkan model runner in `speed_benchmark_torch` to be able to generate inputs for models that have input/output types other than just a single tensor. Input elements are processed depending on their type.
Test Plan: Imported from OSS
Reviewed By: mikaylagawarecki
Differential Revision: D34354839
Pulled By: SS-JIA
fbshipit-source-id: 993e55372d2664fa7eddb16146deba264727f399
(cherry picked from commit 4a140202acb336412676ac090a38d7b93ae49898)