Comment by samplenoise

Doing some form of PQ at train time is possible but typically the goal is to make the model’s embedding layers more robust to quantisation [1][2]. I did some work on this in the recommender systems space [3].

[1] https://arxiv.org/abs/1807.04629

[2] http://proceedings.mlr.press/v119/chen20l/chen20l.pdf

[3] http://ceur-ws.org/Vol-2431/paper10.pdf