specific method · filed under model architecture
SWA-1024
Sliding Window Attention using a 1024-token window, interleaved at a 3:1 ratio.
Also called + SWA-1024 (interleaved 3:1).
- source
- 1
- model
- 1
- labs adopt it
- 0
- strongest
- evaluated
How sources treat it
One count per evidence span, weakest treatment to strongest.
evaluated 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
+ SWA-1024 (interleaved 3:1)
evaluatedmodel architecturein Laguna XS.2Poolside
Filed alongside
Other methods under model architecture :: token mixer :: softmax attention :: sliding window attention.
Sliding Window AttentionHybrid Sliding Window Attention512-token Sliding Window AttentionDecoder SWA Bounded ReplayAlternating Row-Major and Column-Major Token SerializationDynamic Attention Window Size TrainingFixed Sliding Window AttentionPer-Head GatingPure Sliding Window AttentionSink-Augmented Sliding Window AttentionSWA-128