10 citations · 12 across the 5 of their papers we have counts for
4 papers · 1 filter
RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale
Daniel Goldstein, Eric Alcaide, Janna Lu +1
We present Rapid Attention Distillation to Linear Attention Decoders at Scale (RADLADS), a protocol for rapidly converting softmax attention transformers into linear attention deco…
RWKV-7 "Goose" with Expressive Dynamic State Evolution
Bo Peng, Ruichong Zhang, Daniel Goldstein +15
We present RWKV-7 "Goose", a new sequence modeling architecture with constant memory usage and constant inference time per token. Despite being trained on dramatically fewer tokens…
GoldFinch: High Performance RWKV/Transformer Hybrid with Linear Pre-Fill and Extreme KV-Cache Compression
Daniel Goldstein, Fares Obeid, Eric Alcaide +2
We introduce GoldFinch, a hybrid Linear Attention/Transformer sequence model that uses a new technique to efficiently generate a highly compressed and reusable KV-Cache in linear t…
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence
Bo Peng, Daniel Goldstein, Quentin Anthony +27
We present Eagle (RWKV-5) and Finch (RWKV-6), sequence models improving upon the RWKV (RWKV-4) architecture. Our architectural design advancements include multi-headed matrix-value…