Chinese contentLoopFill:面向 Looped Transformer 的免训练流水线多 token 推测解码
搞推理优化的可以看看这篇:LoopFill 把两种草稿器合到一棵树里,免训练就在 Ouro-2.6B 上跑到 5.85 倍加速,比 LoopAhead 快 25%-40%。做 Looped 模型部署或推测解码研究的都该读读原文。
搞推理优化的可以看看这篇:LoopFill 把两种草稿器合到一棵树里,免训练就在 Ouro-2.6B 上跑到 5.85 倍加速,比 LoopAhead 快 25%-40%。做 Looped 模型部署或推测解码研究的都该读读原文。
The key insight is that near-fixed-point recurrent states make much of the compute spent on full backpropagation and full KV caches redundant, cutting costs across training, decoding and RL at once. Practitioners building efficient inference stacks or RL pipelines for recurrent models can apply KV sharing and distilled prefill directly. Compared with Huginn's fixed prior, the learned prior plus orthogonal injection improves perplexity at every scale tested up to 1.6B parameters.