Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Activation Denoising: A Robustness View on Parallel vs Sequential LLM Quantization
Yan Scholten, Rachel Lawrence, James Hensman +3
Post-training quantization is a powerful tool for compressing large language models. The most scalable methods quantize every layer in parallel, but quantization errors then compou…
cs.LG2026
OptRot: Mitigating Weight Outliers via Data-Free Rotations for Post-Training Quantization
Advait Gadhikar, Riccardo Grazzi, James Hensman
The presence of outliers in Large Language Models (LLMs) weights and activations makes them difficult to quantize. Recent work has leveraged rotations to mitigate these outliers. I…