Fast-loading implementation sequence#
- Date:
2026-08
Large-model startup follows one explicit four-document sequence:
fix existing parser, external-data, and initializer-materialization defects in Model-loading bug fixes;
implement Prepared and asynchronous execution;
complete the ownership-aware cross-repository work in Using onnx-light fast loading in onnxruntime;
connect adaptive I/O, model resolution, prepared tensors, and first-token overlap in Completing native fast model loading.
Parallel-for profiling may proceed alongside step 1, but its executor instrumentation must be stable before step 2 begins.