distillation-and-routing-jointly-decouple-capability-from-cost

IN derived (depth 2)

Created 2026-06-21T12:56:38+00:00 · Reviewed 2026-06-21T14:41:08+00:00

Knowledge distillation (validated across the full scale spectrum, from 110M to 2T parameters) and multi-granularity compute routing (intra-model MoE and inter-model task routing) together decouple capability from inference cost along two independent axes: distillation compresses capability into smaller models, while routing allocates compute only where needed — together enabling deployment of frontier-class capability at a fraction of nominal cost.

Justifications

SL — Two independent cost-decoupling mechanisms (compression and conditional computation) operating at complementary levels

Antecedents (all must be IN):

  • IN distillation-validated-across-full-scale-spectrum — Knowledge distillation is validated as a scale-invariant capability across the full spectrum of language model sizes: from BERT-scale (DistilBERT retaining 95% performance at 60% of parameters) to frontier-scale (Llama 4 Maverick codistilled from the unreleased ~2T-parameter Behemoth), demonstrating that larger models reliably compress their capability into smaller ones regardless of absolute scale.
  • IN compute-routing-operates-at-multiple-architectural-granularities — Compute routing in LLMs operates at two distinct architectural granularities: intra-model routing (MoE activating expert subnetwork subsets per token, as in Llama 4) and inter-model routing (GPT-5 selecting between fast and reasoning models per task), demonstrating that conditional computation is a general efficiency principle applicable at both the parameter level and the model-selection level.

Dependents

These beliefs depend on this one: