Comment by visarga

14 days ago

Very interesting trick, using a dictionary of basis vectors which are quickly computed from a seed without storage. But the result is the same 3 or 4 bit quantization, with only a slight improvement. Their tiles are small, just 8 or 12 weights, it's why compression doesn't go too far. It would have been great if this trick lowered quantization <1 bit/weight, that would require longer tiles. Wondering what are the limits if we use a larger reservoir of cheap entropy as part of neural net architecture, even in training.

Congrats to Apple and Meta, makes sense they did the research, this will go towards efficient serving of LLMs on phones. And it's very easy to implement.

I was about to post something similar. While the research is interesting, it doesn’t offer any advantages over 3- or 4-bit quantization. I also have to assume they explored using longer tiles but found it to be ineffective — which would make sense to me from an information theory perspective.

  • > it doesn’t offer any advantages over 3- or 4-bit quantization.

    "zero-shot accuracy retention at 4- and 3-bit compression to be on par with or better than state-of-the-art methods, while maintaining performance comparable to FP16 baselines."

    My reading of that says FP16 accuracy at Q3 or Q4 size / memory bandwidth. Which is a huge advantage.

  • I think the main advantage is that you can compute the extra parameters (the PRNG seeds) from the network weights alone, whereas most other quantization methods require simulating the quantization procedure at training time (Quantization-Aware Training) or setting them from a calibration dataset (Post-Training Quantization)

  • This technique has three significant advantages over popular low bit quantization: 1) it retains more accuracy, 2) it does not require calibration data, 3) it's easier to implement in hardware.

It should be definitely worth it because you can reuse databases of sequence to seed mappings for all future models.