From 3a08e9d4c1a842133be5390924daf51c2263c785 Mon Sep 17 00:00:00 2001 From: Wangwang Wang Date: Mon, 26 Sep 2022 11:09:17 +0800 Subject: [PATCH 1/2] Docs: Fix spelling errors --- docs/OV_Runtime_UG/supported_plugins/GPU.md | 2 +- docs/OV_Runtime_UG/supported_plugins/GPU_RemoteTensor_API.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/OV_Runtime_UG/supported_plugins/GPU.md b/docs/OV_Runtime_UG/supported_plugins/GPU.md index 4033c5d7a2b299..491ce5a6217e03 100644 --- a/docs/OV_Runtime_UG/supported_plugins/GPU.md +++ b/docs/OV_Runtime_UG/supported_plugins/GPU.md @@ -160,7 +160,7 @@ Alternatively, it can be enabled explicitly via the device notion, for example ` @endsphinxtab -@sphinxtab{Bacthing via throughput hint} +@sphinxtab{Batching via throughput hint} @sphinxtabset diff --git a/docs/OV_Runtime_UG/supported_plugins/GPU_RemoteTensor_API.md b/docs/OV_Runtime_UG/supported_plugins/GPU_RemoteTensor_API.md index cbcdd9c92bcb98..6f22307aa452b7 100644 --- a/docs/OV_Runtime_UG/supported_plugins/GPU_RemoteTensor_API.md +++ b/docs/OV_Runtime_UG/supported_plugins/GPU_RemoteTensor_API.md @@ -108,7 +108,7 @@ To request the current default context of the plugin, use one of the following m @endsphinxtab -@sphinxtab{Bacthing via throughput hint} +@sphinxtab{Batching via throughput hint} @snippet docs/snippets/gpu/remote_objects_creation.cpp default_context_from_model From 6e8f4346867e9fdc73101abffcfa4a7d71c007b6 Mon Sep 17 00:00:00 2001 From: Wangwang Wang Date: Mon, 26 Sep 2022 11:11:10 +0800 Subject: [PATCH 2/2] Docs: Update the doc on how to manually set operations affinity --- docs/OV_Runtime_UG/hetero_execution.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/docs/OV_Runtime_UG/hetero_execution.md b/docs/OV_Runtime_UG/hetero_execution.md index 1b802eb2793dfa..7994e5e803de66 100644 --- a/docs/OV_Runtime_UG/hetero_execution.md +++ b/docs/OV_Runtime_UG/hetero_execution.md @@ -31,6 +31,9 @@ Following the OpenVINO™ naming convention, the Hetero execution plugin is assi #### The Manual Mode It assumes setting affinities explicitly for all operations in the model using `ov::Node::get_rt_info` with the `"affinity"` key. +If you assign specific operation to a specific device, make sure that the device actually supports the operation. +Randomly selecting operations and setting affinities may lead to decrease in model accuracy. To avoid that, try to set the related operations or subgraphs of this operation to the same affinity, such as the constant operation that will be folded into this operation. + @sphinxtabset @sphinxtab{C++}