SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models — mentioned by boulos

Sat, 09 Nov 2024 18:30:11 GMT

As others have replied, this is reasonable general feedback, but in this specific case the work was done carefully. Table 1 from the linked paper (https://arxiv.org/pdf/2411.05007) includes a variety of metrics, while an entire appendix is dedicated to quality comparisons. By showing their work side-by-side with other quantization schemes, you can also see a great example of the flavor of different results you can get with these slight tweaks (e.g., ViDiT INT8) and that their quantization does a much better job in reproducing the "original" (Figure 15). In this application, it's not strictly…

Paper and discussion history. A mention is not an endorsement.

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models · HackerPapers discussions

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models — mentioned by boulos