TriRoute: Unified Learned Routing for Joint Adaptive Attention, Experts, and KV-Cache Allocation

arXiv:2607.06601v1 Announce Type: new Abstract: Conditional computation can decouple language model quality from per-token inference cost, yet leading techniques act on a single axis in isolation: Mixture-of-Experts (MoE) sparsifies the FFN, Mixture-of-Depths (MoD) skips whole transformer blocks, and KV-cache quantization compresses attention memory. We argue these three decisions (attention resolution, expert selection, and cache bit-width) are strongly coupled and should be made jointly: a tok...