Author

J. Ju

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

SiFAR: Synchronization-Free All-Reduce for Low-Latency LLM Inference

Speculative reduction is proposed, which initiates data transfer before the top barrier and ensures correctness via lightweight validation during low-latency inference, which reduces synchronization overhead during low-latency inference.

Hritvik Taneja, A. Saxena, Abhishek Revinipati et al. · arXiv.org · 1 citation