pytorch

9981aade - [Quant][core][devs] Separated implementations for quantized & non-quantized tensors in index_select_cuda (#72407)

[Quant][core][devs] Separated implementations for quantized & non-quantized tensors in index_select_cuda (#72407) Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/72407 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 separates the calls to quantized & non-quantized backends for index_select_cuda using a dispatcher. Differential Revision: D34035694 D34035694 Test Plan: Imported from OSS Reviewed By: jerryzh168 Pulled By: dzdang fbshipit-source-id: ff66b0c6c1be841a6cfaaa3339e7b0b19260708e (cherry picked from commit f92c008d8eb58a6c4b4d0132bd592ce70d1bdce7)