Cutedsl Tunable Kernel Template

Adds an Attention Gym tuning adapter to a CuTeDSL op using typed input-aware configs, cached fake-tensor TVM-FFI compilation, parallel candidate compilation, and sequential GPU benchmarking. Use after the core kernel exists and needs a public default, explicit-config, or autotune path.

meta-pytorch Updated
Two new Flexys—Sparse Attention and Linear Attention—enter Attention Gym while the original Flexys train

File contents

meta-pytorch/attention-gym commit 4f92ee5c6d

Frequently asked questions

npx get-skill add meta-pytorch/cutedsl-tunable-kernel-template