Add missing quantize per tensor vulkan backend function (#106641)
Summary: Add missing function for vulkan namespace for quantization
Test Plan:
Check that a quantized model runs on Vulkan.
Notebook tested: https://www.internalfb.com/intern/anp/view/?id=4045081
Differential Revision: D48047516
Pull Request resolved: https://github.com/pytorch/pytorch/pull/106641
Approved by: https://github.com/SS-JIA