mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-18 21:21:17 +00:00
2c50b75a26
### Description Inline functions in an EP aware fashion. The result of this PR is that models that are having been inlined by ONNX inliner and optimized and models that have been AOT inlined appear to be visually identical. For tests I used two models. The only difference is the resulting size because ONNX inliner removes local function definitions and AOT does not. Difference in sizes for `HF Mobile` model was 2.5 MB, and for `HF Bart` it was ~500K. It seems that the resuling model size affects the load time more than the actual optimizations. In general, the inlined models grow in size very fast and can easily exceed 2Gb limit. Q. Should we make AOT optional? `If` costant folding and the removal of local inlined models will be coming in other PRs. Some stats:  |
||
|---|---|---|
| .. | ||
| basic_types.h | ||
| constants.h | ||
| function.h | ||
| graph.h | ||
| graph_nodes.h | ||
| graph_viewer.h | ||
| indexed_sub_graph.h | ||
| node_arg.h | ||
| schema_registry.h | ||