Continuous depth batching schedules each loop iteration of a depth-adaptive looped language model separately, reaching up to 99% of the theoretical adaptive-depth speedup.
Scaling laws meet model architecture: Toward inference-efficient LLM s
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
-
Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching
Continuous depth batching schedules each loop iteration of a depth-adaptive looped language model separately, reaching up to 99% of the theoretical adaptive-depth speedup.