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.
Accelerating distributed moe training and inference with lina,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.