[Quant][core][devs] Removed support for non-quantized tensors in reflection_pad1d_cpu (#72485)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/72485
This PR is part of a series of PRs addressing https://github.com/pytorch/pytorch/issues/54150,
related to using dispatcher for calls to quantized backends as opposed to if/else conditionals.
This particular PR removes the support for non-quantized tensors in reflection_pad1d_cpu because the current dispatch table for the 2 argument reflection_pad1d_cpu only has a QuantizedCPU entry that routes to reflection_pad1d_cpu; all other backends are routed through structured_delegate's desgination which then through through the out variant overload
Test Plan: Imported from OSS
Reviewed By: jerryzh168
Differential Revision: D34085104
Pulled By: dzdang
fbshipit-source-id: 26c3ac21d787641571f8c52157b037bf14c9d500
(cherry picked from commit 019704ae0551767f7f6b049f59d8701ba4bec17c)