Gated DeltaNet: Causal Depthwise Convolution
Medium · Solved in PyTorch · Machine learning coding practice
Problem
Mix local token history independently in each channel, then apply SiLU.
Topics: gated-deltanet, linear-attention, llm-internals
The full statement, worked examples, hints and the test suite are available once you sign in. You can then solve Gated DeltaNet: Causal Depthwise Convolution in the browser and run it against the tests.