Hasn't this been the case for a while? I vaguely remember using the optimal e8 packing to try to get denser product quantization for vector embeddings.

▲

corndoge 2 hours ago | parent | next [-]

She proved it

▲

wyndyl 2 hours ago | parent | prev [-]

How did you apply e8 to vector embeddings?

	▲	Scene_Cast2 an hour ago \| parent [-]
		Chunk up your 128D embedding into 16 8D pieces, then quantize using the optimal packing points. Performs worse than k-means in my experience.