TokenGate
Named by 2 kept items in this workspace.
Search every workspace for TokenGate. It matches the name as written, so it can find other things that share it.
The items that name it 2
Token-gated attention method for faster long-context prefill, with GitHub repo supporting Qwen 3.5-style architectures.
Small, drop-in component that extends existing trained models to enable end-to-end learnable token pruning over long-context inputs for fast, memory-efficient prefill. Code is released by the authors.
All technologies in this workspace.