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.
FasterMoE: modeling and optimizing training of large- scale dynamic pre-trained models,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
RouterBench supplies a standardized benchmark, 405k+ inference dataset, theoretical framework, and comparative analysis for multi-LLM routing systems.
DODOCO measurements show MoE routing imbalance is intrinsic to architecture and real text, not correctable by EP scaling or represented by mock tokens, forming two persistent Gini bands.
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.
-
Diagnosing Overhead in Dispatch Operations: Cross-architecture Observatory
DODOCO measurements show MoE routing imbalance is intrinsic to architecture and real text, not correctable by EP scaling or represented by mock tokens, forming two persistent Gini bands.