20384 (opens in new tab)

#Python Use CapabilityBasedPartitioner in AotiPartitioner (Summary: AotiPartitioner (the base for the CUDA and Metal backends) groups the ops it delegates into one partition, by hand. Every other ExecuTorch backend (XNNPACK, Vulkan, CoreML) uses the shared CapabilityBasedPartitioner helper instead. This switches AotiPartitioner to that helper too. Why: Consistency -- same partitioning path as the other backends, and a real OperatorSupport hook instead of a hand-rolled tagging loop. It can bre...

Read the original article