Back to papers
October 19, 2026cs.CLcs.AI

TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning

Liana Patel, Rishabh Ranjan, Ion Stoica, Matei Zaharia, Carlos Guestrin
Read on arXivDownload PDF
HF Upvotes

1

Categories

cs.CL, cs.AI

TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning - AI | One9Founders