资讯

Researchers from Stanford and UC Berkeley Introduce TokenGate: Token-Gated Attention Makes Long-Context Prefill Up to 11.3x Faster

📅 2026-10-25 · AI导航编辑部

Stanford and UC Berkeley researchers released TokenGate, a drop-in learned token pruning module for LLMs. It cuts long-c

Stanford and UC Berkeley researchers released TokenGate, a drop-in learned token pruning module for LLMs. It cuts long-context prefill time-to-first-token by 1.4x to 11.3x and peak memory by 1.5x to 3.4x without accuracy loss.

The post Researchers from Stanford and UC Berkeley Introduce TokenGate: Token-Gated Attention Makes Long-Context Prefill Up to 11.3x Faster appeared first on MarkTechPost.

来源：https://www.marktechpost.com/2026/10/25/stanford-berkeley-tokengate-learned-token-pruning-llm-prefill/