pith. sign in

org/abs/2412.18110v1

URL https://arxiv · arXiv 2412.18110

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
read on arXiv browse 1 citing papers

fields

cs.LG 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

RAP: Runtime Adaptive Pruning for LLM Inference

cs.LG · 2025-05-22 · unverdicted · novelty 5.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • RAP: Runtime Adaptive Pruning for LLM Inference cs.LG · 2025-05-22 · unverdicted · none · ref 22

    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.