pytorch

bb3e1f30 - [Pytorch NNAPI] Add compilation_preference & relax_f32_to_f16 APIs (#78758)

[Pytorch NNAPI] Add compilation_preference & relax_f32_to_f16 APIs (#78758) Summary: compilation_preference is one of: ANEURALNETWORKS_PREFER_LOW_POWER = 0 ANEURALNETWORKS_PREFER_FAST_SINGLE_ANSWER = 1 ANEURALNETWORKS_PREFER_SUSTAINED_SPEED = 2 relax_f32_to_f16 calls Model_relaxComputationFloat32toFloat16 Test Plan: Tested on device with nnapi models * Works with existing exported models * Works with new exported models with options Differential Revision: D36433236 Pull Request resolved: https://github.com/pytorch/pytorch/pull/78758 Approved by: https://github.com/kimishpatel