PPL
Dan Alistarh
Papers (4)
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained TransformersApertus LLM Family Expansion via Distillation and QuantizationGrid Games: The Power of Multiple Grids for Quantizing Large Language ModelsMatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning