← Search

Yair Hanani

2 accepted papers

2025

Tensor-Parallelism with Partially Synchronized Activations

NeurIPS 2025poster

Training and inference of Large Language Models (LLMs) with tensor-parallelism requires substantial communication to synchronize activations. Our findings suggest that with a few minor adjustments to current practices, LLMs can be trained without fully synchronizing activations, reducing bandwidth d…

Cited by 0SourceScholar
2021

Accurate Post Training Quantization With Small Calibration Sets

ICML 2021spotlight

Lately, post-training quantization methods have gained considerable attention, as they are simple to use, and require only a small unlabeled calibration set. This small dataset cannot be used to fine-tune the model without significant over-fitting. Instead, these methods only use the calibration set…