pytorch

2a23dfe8 - [quant] Support lowering for quantized embedding byte operator (#91159)

[quant] Support lowering for quantized embedding byte operator (#91159) Summary: This PR adds lowering for embedding in quantization in executorch flow Test Plan: buck run executorch/exir/tests:quant_fusion_pass -- "executorch.exir.tests.test_quant_fusion_pass.TestQuantFusionPass.test_embedding_byte" Reviewed By: qihqi Differential Revision: D41673139 Pull Request resolved: https://github.com/pytorch/pytorch/pull/91159 Approved by: https://github.com/vkuzo