Quantize embedding op and 16x8 matmul#2

shewu-quic wants to merge 2 commits intocccclai:export-D63736779cccclai/executorch-1:export-D63736779from

CodeLinaro:dev1/hutton/quantize_embedding_and_16x8_matmulCodeLinaro/executorch:dev1/hutton/quantize_embedding_and_16x8_matmulCopy head branch name to clipboard