onnxruntime

b8609880 - Save much memory at model loading time by converting weights to OrtValues early (#26345)

Save much memory at model loading time by converting weights to OrtValues early (#26345) ### Description Converts weights early and revert "Properly remove in-memory references (#25652)" This reverts commit 3ca49d88017cfbf90f23b7d85426ab2da0a9e1a9 and makes appropriate adjustments for the current state of the code. This PR is made possible and on the heels of: https://github.com/microsoft/onnxruntime/pull/26263 https://github.com/microsoft/onnxruntime/pull/25833. Previous history: https://github.com/microsoft/onnxruntime/pull/23979 https://github.com/microsoft/onnxruntime/pull/25320 https://github.com/microsoft/onnxruntime/pull/25626 https://github.com/microsoft/onnxruntime/pull/25652 The first change (https://github.com/microsoft/onnxruntime/pull/26263) allows us to convert initializers to OrtValues early and save lots of memory at model loading time. Specifically, for Phi-4-mini-instruct-INT4 model before and after looks like this: **Before** <img width="1204" height="124" alt="Before change DEBUG 2025-10-16 144819" src="https://github.com/user-attachments/assets/674ff75b-057f-498a-a906-0140d59d46e6" /> **After** <img width="997" height="114" alt="After change DEBUG 2025-10-16 144819" src="https://github.com/user-attachments/assets/df1783af-7f50-4cd2-b3ad-6868f23be53f" /> The two peaks represent memory usage at optimization time (8.1Gb before) and after weights memory mapping (6.5Gb) After this change corresponding numbers look 3.5Gb and 4.7Gb respectively. Most of the savings during optimization phase come from `ConstantFolding` where we are able to reuse the resulting OrtValues directly for the new initializers. This PR concludes a series of PRs converting initializers to OrtValues. Memory consumption before the conversion began was 9.3Gb and 6.7Gb respectively. We are saving almost 6Gb during optimization and 2Gb for the steady state. <img width="1175" height="139" alt="image" src="https://github.com/user-attachments/assets/80e7d228-8a8e-4316-8e04-b02c2be30f04" /> The model also loads about 12 seconds faster. Example of ConstantFolding being one of the top contributors where we duplicate memory for higher peak before Resolve takes care of no longer used initializers. <img width="1100" height="558" alt="Sanpshot 3 Peak on ConstantFolding Transpose Optimizer" src="https://github.com/user-attachments/assets/95545abd-3f99-46d9-862e-bbf27cbb5b40" /> <img width="1060" height="600" alt="Snapshot 4 Peak AddInitializer from ConstantFolding" src="https://github.com/user-attachments/assets/dd457ec6-23ee-4efd-8c60-625d5faad61e" /> <img width="325" height="160" alt="image" src="https://github.com/user-attachments/assets/37c1194d-f683-49a7-afb1-073dfbb9bbfc" /> ### 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. --> Reduce memory usage.