2 papers
cs.LG2026
HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion Models
Yuval Domb, Hadar Sackstein, Tomer Solberg
We present HyperQuant (Hadamard, optimallY Packing, Entropy Rice-coding), a unified post-training quantization pipeline for the weights and the KV cache of large language and diffu…
hep-th2018
The action of long strings in supersymmetric field theories
Tomer Solberg, Mykhailo Yutushui
Long strings emerge in many Quantum Field Theories, for example as vortices in Abelian Higgs theories, or flux tubes in Yang-Mills theories. The actions of such objects can be expa…