A shared per-token controller jointly routes attention resolution, FFN experts, and KV bit-width and is claimed to Pareto-dominate independently tuned MoD+MoE+KV-quant at matched cost while protecting rare-token accuracy.
MegaBlocks: Efficient sparse training with mixture-of-experts
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TriRoute: Unified Learned Routing for Joint Adaptive Attention, Experts, and KV-Cache Allocation
A shared per-token controller jointly routes attention resolution, FFN experts, and KV bit-width and is claimed to Pareto-dominate independently tuned MoD+MoE+KV-quant at matched cost while protecting rare-token accuracy.