[torchao/ExecuTorch] move embedding quantization to torchao #9514
Description
🚀 The feature, motivation and pitch
Move the EmbeddingQuantizer in ET llama code to torchao and write it using torchao quant primitives. Recombine embedding Q/DQ ops into packed weights during to_executorch.
Alternatives
No response
Additional context
No response
RFC (Optional)
No response