Post
244
Existing methods β GPTQ, AWQ, llama.cpp's k-quants β minimize empirical loss heuristically. None of them prove they are optimal in any information-theoretic sense. ICRB-Q builds a quantization scheme that is provably optimal via the CramΓ©r-Rao lower bound (CRB): no unbiased estimator of a weight can have lower variance than [F(ΞΈ)]β»ΒΉ, where F is the Fisher information matrix.