ReaLB balances multimodal MoE inference loads by switching vision-heavy experts to lower FP4 precision per device rank, hiding the change in the dispatch phase to deliver 1.10-1.32x speedup with <1% accuracy degradation.
Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming , pages =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
RouterBench supplies a standardized benchmark, 405k+ inference dataset, theoretical framework, and comparative analysis for multi-LLM routing systems.
citing papers explorer
-
ReaLB: Real-Time Load Balancing for Multimodal MoE Inference
ReaLB balances multimodal MoE inference loads by switching vision-heavy experts to lower FP4 precision per device rank, hiding the change in the dispatch phase to deliver 1.10-1.32x speedup with <1% accuracy degradation.
-
RouterBench: A Benchmark for Multi-LLM Routing System
RouterBench supplies a standardized benchmark, 405k+ inference dataset, theoretical framework, and comparative analysis for multi-LLM routing systems.