Frank Dong c5b6be045f enable serialize prepacked weights into data file (#22256) ... ### Description part of https://github.com/microsoft/onnxruntime/issues/21448 This change is intend to save CPU memory during model load for inference. Added session option save_prepacked_constant_initializers, with save_prepacked_constant_initializers turn on: 1. optimize model with inference session, prepacked external initializer will be saved into data file. 2. load optimized model and external data file with prepacked initializer, no prepack is needed 3. run inference with optimized model and data file Tested with model Phi-3-mini-instruct-onnx, with ORT 1.12.0:  with this change:  Peak memory usage dropped from **5.438 GB to 2.726GB**. This change takes advantage of ORT loads external initializer with mmap on CPU. Prepack will use extra memory on heap, omit prepack process can save this part of memory (roughly same size as external initializers). next step: Change all the kernels on CPU with PrePack method implemented and test properly. Will do in next PR. ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. -->		2024-10-24 22:24:48 -07:00
..
orttraining	enable serialize prepacked weights into data file (#22256)	2024-10-24 22:24:48 -07:00
tools	Update ruff and clang-format versions (#21479)	2024-07-24 11:50:11 -07:00