arXiv· Liana Patel·· 11 天前
TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning
TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning
来源：arXiv · arxiv.org
TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning