pytorch
3727baea - [PyTorch Edge][Model Loading] Operator Call De-dup at TorchScript Serialization Level [2/2] (#64269)

Commit
4 years ago
[PyTorch Edge][Model Loading] Operator Call De-dup at TorchScript Serialization Level [2/2] (#64269) Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/64269 Revert changes in D29826210 (https://github.com/pytorch/pytorch/commit/693d8f2f0767413bb995b895fccad87dfd4f05a7) (we don't need operator lambda caching since there aren't duplicate operators anymore) This diff stack results in an additional approx 12% speedup in model loading time (from 229ms to 200ms) when run against an 87MB speech model that jiatongzhou provided. ghstack-source-id: 138014904 Test Plan: **Speech Transducer v25 model (as in D29826210 (https://github.com/pytorch/pytorch/commit/693d8f2f0767413bb995b895fccad87dfd4f05a7))** || Before | After | |Load Time|[229ms](https://www.internalfb.com/intern/aibench/details/160889436133243)|[200ms](https://www.internalfb.com/intern/aibench/details/837884532607514)| |Save File Size|[86.23 MB](https://lookaside.facebook.com/intern/diff/file/data/?number=658544950)|[86.1 MB](https://lookaside.facebook.com/intern/diff/file/data/?number=658554403)| The "after" flamegraph shows significantly less time is spent on ```append_operator``` than before. Steps - Check out desired commit in devserver (base branch or this diff) - ```buck build bento/kernels:bento_kernel_pytorch``` - Use N1094068 with pytorch_local kernel to save model for lite interpreter - Edit ```aibench/specifications/models/pytorch/speech_transducer/v25.json ``` to have new model location and md5 - ```buck run aibench:run_bench -- -b aibench/specifications/models/pytorch/speech_transducer/v25.json --framework pytorch --platform android/arm64 --devices "S8US" --force_profile --remote ``` **Test that saving a model with de-dup ops doesn't change its output** https://www.internalfb.com/intern/anp/view/?id=1137434 Reviewed By: iseeyuan Differential Revision: D30615710 fbshipit-source-id: bb4052f0f16eccab386585e94411056f94bce43c
Author
Parents
Loading