mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-22 19:23:30 +00:00
76434907fb
This adds a new "Graph Capture" option to the DML ep, similar to the cuda graph functionality. Here's how graph capture works: - A user can enable graph capture in the session options by setting `ep.dml.enable_graph_capture` to `true` - When they want to capture a run, they set `gpu_graph_id` in their `RunOptions` to a number bigger than 0 (0 is reserved for internal use according to the cuda graph documentation). - Then, when they start the inference, the graph will be captured and stored in the DML EP for future use - When they execute the run for a second time with the same id, the `ReplayGraph` function in the DML EP will be called instead of executing the kernels, resulting in very low overhead and avoiding kernel recompilation. This feature can give up-to-par or even better performance than specifying the static dimensions at session creation time, but is also much more flexible. |
||
|---|---|---|
| .. | ||
| codegen | ||
| common | ||
| dll | ||
| dlpack | ||
| eager | ||
| flatbuffers | ||
| framework | ||
| graph | ||
| language_interop_ops | ||
| mickey | ||
| mlas | ||
| optimizer | ||
| platform | ||
| providers | ||
| quantization | ||
| session | ||
| util | ||