RAP is a reinforcement learning framework for runtime-adaptive pruning of LLMs that jointly optimizes model weights and KV-cache usage under varying memory budgets.
By removing a fraction of the attention layers based on cosine similarity-based importance, this approach achieves notable speedups with minor impact on the model performance
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RAP: Runtime Adaptive Pruning for LLM Inference
RAP is a reinforcement learning framework for runtime-adaptive pruning of LLMs that jointly optimizes model weights and KV-cache usage under varying memory budgets.