ForkAttention
ForkAttention is the core mechanism of the Flide engine. It encodes the logical tree structure of a decision request as GPU-resident indices and exactly forks states over a flattened token stream, ensuring that each query branch's computation matches an isolated forward pass under exact arithmetic.
Timeline (last 90 days)
The core innovation of Flide is ForkAttention, which does not treat each branch as an independent request but instead encodes the logical tree structure of the entire decision request as a GPU-resident index and executes on a single flattened token stream.
For both standard attention layers and recurrent Gated DeltaNet layers, ForkAttention can navigate request dependencies according to these indices, ensuring that the computation results of each query branch are exactly consistent with isolated forward propagation.
All Facts (2)
The core innovation of Flide is ForkAttention, which does not treat each branch as an independent request but instead encodes the logical tree structure of the entire decision request as a GPU-resident index and executes on a single flattened token stream.
50%UnverifiedFor both standard attention layers and recurrent Gated DeltaNet layers, ForkAttention can navigate request dependencies according to these indices, ensuring that the computation results of each query branch are exactly consistent with isolated forward propagation.
50%