mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-06-28 03:20:58 +00:00
1de79d3158
- Add 64-bit for those which now support true 64-bit (Gather, Scatter, OneHot, Cast), and update others (ArgMin, ArgMax, ReverseSequence, TopK, MaxPool, MaxUnpool) which take 64-bit indices but use strided 32-bit fallback. - Stop forcibly coercing all 64-bit tensors in TensorDesc. Instead, decide in the respective kernels how to behave. - Update graph partitioning code with enough registration information to know whether (a) 64-bit tenors are not supported at all (b) they are support via strided 32-bit fallback (c) they are supported via fallback and directly (preferred when device capable). Unfortunately this introduces a lot of flag parameters :/. Related work items: #22265955 |
||
|---|---|---|
| .. | ||
| abi_custom_registry_impl.cpp | ||
| abi_custom_registry_impl.h | ||
| pch.h | ||
| winml_adapter_apis.h | ||
| winml_adapter_c_api.cpp | ||
| winml_adapter_c_api.h | ||
| winml_adapter_dml.cpp | ||
| winml_adapter_environment.cpp | ||
| winml_adapter_execution_provider.cpp | ||
| winml_adapter_model.cpp | ||
| winml_adapter_model.h | ||
| winml_adapter_session.cpp | ||