Expand description
Compatibility exports for the canonical Etalon Qwen engine.
Structs§
Enums§
Functions§
- execute_
streamed_ final_ hyper_ connection - Execute Qwen4Exp’s final global Hyper-Connection mixer. Unlike a layer
mixer it has no injection projection: the collapsed hidden vector feeds
the vocabulary projection directly in place of an
output_normtensor. - execute_
streamed_ hyper_ connection - Stream one attention or FFN Hyper-Connection mix from the trunk.
- inject_
hyper_ update - Scatter a token-mixer/MoE branch back into each residual stream. Qwen4Exp uses one learned inject scalar per stream, divided by the stream count.
- mix_
hyper_ streams - Form the hidden-width mixer input from the learned per-stream gates.