G^2PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation
G2PTQ refreshes gradients and Hessians during LLM quantization, beating GPTQ-style baselines.
1 stories, newest first · one card per story
G2PTQ refreshes gradients and Hessians during LLM quantization, beating GPTQ-style baselines.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views