SPRINT prunes Transformer sublayers using latency-aware importance scores and post-tuning sensitivity, achieving better accuracy-speedup trade-offs on Llama models than prior pruning methods.
Pea-kd: Parameter-efficient and accurate knowledge distillation on bert
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information
SPRINT prunes Transformer sublayers using latency-aware importance scores and post-tuning sensitivity, achieving better accuracy-speedup trade-offs on Llama models than prior pruning methods.