GPTQ is equivalent to Babai's nearest plane algorithm for CVP on the Hessian lattice of layer inputs, yielding geometric interpretation, inherited error bounds, and improved clipping-free quantization with GPU kernels.
4 Jerry Chee, Yaohui Cai, Volodymyr Kuleshov, and Christopher M De Sa
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Waterfilling rate allocation makes quantized matrix multiplication for LLMs near information-theoretically optimal, with WaterSIC being basis-free and within 0.25 bits per entry of the limit.
High-rate quantization theory yields accurate approximations for the distortion of absmax INT and FP schemes in generic weight-plus-activation matrix multiplication.
citing papers explorer
-
The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm
GPTQ is equivalent to Babai's nearest plane algorithm for CVP on the Hessian lattice of layer inputs, yielding geometric interpretation, inherited error bounds, and improved clipping-free quantization with GPU kernels.
-
High-Rate Quantized Matrix Multiplication II
Waterfilling rate allocation makes quantized matrix multiplication for LLMs near information-theoretically optimal, with WaterSIC being basis-free and within 0.25 bits per entry of the limit.
-
High-Rate Quantized Matrix Multiplication I
High-rate quantization theory yields accurate approximations for the distortion of absmax INT and FP schemes in generic weight-plus-activation matrix multiplication.