Smaller activation outliers do not necessarily imply better low-bit quantization: their alignment with the quantizer matters. We introduce PrismQuant, a quantizer-aware rotation framework that aligns the leading activation eigenspace with the constant group subspace of asymmetric grouped INT4. The affine offsets repres...
Yan-Long Chen, Yi-Ning Chen, Song Zhang et al.· 0 citations
This work introduces PrismQuant, a quantizer-aware rotation framework that aligns the leading activation eigenspace with the constant group subspace of asymmetric grouped INT4, and formulate rotation design as a Ky Fan trace maximization and derive a closed-form solution that is provably optimal for this alignment obje...
Yan-Long Chen, Yi-Ning Chen, Song Zhang et al.· 0 citations
This work introduces S-CEReBrO (Streaming CEReBrO), an evolution of the CEReBrO architecture designed for continuous monitoring that factorizes attention computation into fixed-size spatiotemporal windows, so that under streaming, only the active window remains resident and the attention state is bounded independently...
G. Bucagu, T. Ingolfsson, Yawei Li et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.