From a8bce5b3bf7a3307433a090461fa986ec6fe6913 Mon Sep 17 00:00:00 2001 From: Hector Li Date: Mon, 13 Nov 2023 14:03:29 -0800 Subject: [PATCH] [QNN EP] QNN EP doc update (#18399) ### Description Add more EP options enabled recently --- .../QNN-ExecutionProvider.md | 24 ++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/docs/execution-providers/QNN-ExecutionProvider.md b/docs/execution-providers/QNN-ExecutionProvider.md index 00c1630a06dac..8772ec75629e6 100644 --- a/docs/execution-providers/QNN-ExecutionProvider.md +++ b/docs/execution-providers/QNN-ExecutionProvider.md @@ -74,6 +74,28 @@ The QNN Execution Provider supports a number of configuration options. The `prov |'/path/to/context/cache'|string path to context cache binary| +|`provider_options_values` for `provider_options_keys = "qnn_context_embed_mode"`|Description| +|---|---| +|'0'|generate the QNN context binary into separate file, set path in ONNX file specified by qnn_context_cache_path.| +|'1'|generate the QNN context binary into the ONNX file specified by qnn_context_cache_path (default).| + + +|`provider_options_values` for `provider_options_keys = "qnn_context_priority"`|[Description](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/htp_yielding.html)| +|---|---| +|'low'|| +|'normal'|default.| +|'normal_high'|| +|'high'|| + + +|`provider_options_values` for `provider_options_keys = "htp_graph_finalization_optimization_mode"`|Description| +|---|---| +|'0'|default.| +|'1'|faster preparation time, less optimal graph.| +|'2'|longer preparation time, more optimal graph.| +|'3'|longest preparation time, most likely even more optimal graph.| + + ## Usage ### C++ C API details are [here](../get-started/with-c.md). @@ -94,4 +116,4 @@ sess = ort.InferenceSession(model_path, providers=['QNNExecutionProvider'], prov ### Inference example -[Image classification with Mobilenetv2 in CPP using QNN Execution Provider with QNN CPU & HTP Backend](https://github.com/microsoft/onnxruntime-inference-examples/tree/main/c_cxx/QNN_EP) +[Image classification with Mobilenetv2 in CPP using QNN Execution Provider with QNN CPU & HTP Backend](https://github.com/microsoft/onnxruntime-inference-examples/tree/main/c_cxx/QNN_EP/mobilenetv2_classification)