[GPU] Fix default value of KEY_GPU_MODEL_PRIORITY (openvinotoolkit#8398)

docs/IE_DG/supported_plugins/GPU.md

@@ -105,7 +105,7 @@ When specifying key values as raw strings (that is, when using Python API), omit
 | `KEY_CACHE_DIR`      | `"<cache_dir>"`                    | `""`              | Specifies a directory where compiled OCL binaries can be cached. First model loading generates the cache, and all subsequent LoadNetwork calls use precompiled kernels which significantly improves load time. If empty - caching is disabled             |
 | `KEY_PERF_COUNT`      | `YES` / `NO`                    | `NO`              | Collect performance counters during inference             |
 | `KEY_CONFIG_FILE`     | `"<file1> [<file2> ...]"`         | `""`              | Load custom layer configuration files                     |
-| `KEY_GPU_MODEL_`<br>`PRIORITY` | `GPU_MODEL_PRIORITY_<HIGH\|LOW>`  <br/> `GPU_QUEUE_PRIORITY_<LOW\|HIGH\|MED\|DISABLED>`   <br/> `GPU_HOST_TASK_PRIORITY_<HIGH\|LOW\|ANY>`  | `GPU_QUEUE_PRIORITY_DEFAULT` <br/>  `\|GPU_HOST_TASK_PRIORITY_ANY`             | Specifies two types of priority: host task priority and OpenCL queue priority.<br/><br/>Host task priority is specified by `GPU_HOST_TASK_PRIORITY_[level]` and there are three types of task levels: `HIGH`, `LOW`, and `ANY`. Note that `HIGH` and `LOW` are effective only when tbb is used for multithreading the LoadNetwork workload and the host processor is hybrid type. For hybrid processors, if the task priority type is set as `HIGH` the task will have higher priority for core type selection, and vice versa. If the host processor is not hybrid core or the multi threading is not using tbb, it is set as `ANY`, which is the default type.<br/><br/>OpenCL queue priority is specified by `GPU_QUEUE_PRIORITY_[level]` and there are four types of levels: `HIGH`, `MED`, `LOW`, and `DEFAULT`, where the default value is `DEFAULT`. Before usage, make sure your OpenCL driver supports appropriate extension.<br/><br/>Basically `GPU_MODEL_PRIORITY` can be set as combination of the two priority types, such as<br/>-`GPU_QUEUE_PRIORITY_HIGH\|GPU_HOST_TASK_PRIORITY_HIGH` or<br/>-`GPU_QUEUE_PRIORITY_LOW\|GPU_HOST_TASK_PRIORITY_HIGH`.<br/><br/>Also it can be set as a more abstract level of priority PLUGIN_PRIORIY_[level], which represents combination of the two priorities as follows:<br/>-`GPU_MODEL_PRIORITY_HIGH` : `GPU_QUEUE_PRIORITY_HIGH\|GPU_HOST_TASK_PRIORITY_HIGH`<br/>-`GPU_MODEL_PRIORITY_LOW` : `GPU_QUEUE_PRIORITY_LOW\|GPU_HOST_TASK_PRIORITY_LOW`<br/><br/>The default of `KEY_GPU_MODEL_PRIORITY` is `GPU_QUEUE_PRIORITY_DEFAULT\|GPU_HOST_TASK_PRIORITY_ANY`.<br>  |
+| `KEY_GPU_MODEL_`<br>`PRIORITY` | `GPU_MODEL_PRIORITY_<HIGH\|LOW>`  <br/> `GPU_QUEUE_PRIORITY_<LOW\|HIGH\|MED\|DEFAULT>`   <br/> `GPU_HOST_TASK_PRIORITY_<HIGH\|LOW\|ANY>`  | `GPU_QUEUE_PRIORITY_DEFAULT` <br/>  `\|GPU_HOST_TASK_PRIORITY_ANY`             | Specifies two types of priority: host task priority and OpenCL queue priority.<br/><br/>Host task priority is specified by `GPU_HOST_TASK_PRIORITY_[level]` and there are three types of task levels: `HIGH`, `LOW`, and `ANY`. Note that `HIGH` and `LOW` are effective only when tbb is used for multithreading the LoadNetwork workload and the host processor is hybrid type. For hybrid processors, if the task priority type is set as `HIGH` the task will have higher priority for core type selection, and vice versa. If the host processor is not hybrid core or the multi threading is not using tbb, it is set as `ANY`, which is the default type.<br/><br/>OpenCL queue priority is specified by `GPU_QUEUE_PRIORITY_[level]` and there are four types of levels: `HIGH`, `MED`, `LOW`, and `DEFAULT`, where the default value is `DEFAULT`. Before usage, make sure your OpenCL driver supports appropriate extension.<br/><br/>Basically `GPU_MODEL_PRIORITY` can be set as combination of the two priority types, such as<br/>-`GPU_QUEUE_PRIORITY_HIGH\|GPU_HOST_TASK_PRIORITY_HIGH` or<br/>-`GPU_QUEUE_PRIORITY_LOW\|GPU_HOST_TASK_PRIORITY_HIGH`.<br/><br/>Also it can be set as a more abstract level of priority PLUGIN_PRIORIY_[level], which represents combination of the two priorities as follows:<br/>-`GPU_MODEL_PRIORITY_HIGH` : `GPU_QUEUE_PRIORITY_HIGH\|GPU_HOST_TASK_PRIORITY_HIGH`<br/>-`GPU_MODEL_PRIORITY_LOW` : `GPU_QUEUE_PRIORITY_LOW\|GPU_HOST_TASK_PRIORITY_LOW`<br/><br/>The default of `KEY_GPU_MODEL_PRIORITY` is `GPU_QUEUE_PRIORITY_DEFAULT\|GPU_HOST_TASK_PRIORITY_ANY`.<br>  |
 | `KEY_GPU_PLUGIN_`<br>`PRIORITY` | `<0-3>`                       | `0`               | OpenCL queue priority (before usage, make sure your OpenCL driver supports appropriate extension)<br> Higher value means higher priority for OpenCL queue. 0 disables the setting. **Deprecated**. Please use KEY_GPU_MODEL_PRIORITY |
 | `KEY_GPU_PLUGIN_`<br>`THROTTLE` | `<0-3>`                       | `0`               | OpenCL queue throttling (before usage, make sure your OpenCL driver supports appropriate extension)<br> Lower value means lower driver thread priority and longer sleep time for it. 0 disables the setting. |
 | `KEY_CLDNN_ENABLE_`<br>`FP16_FOR_QUANTIZED_`<br>`MODELS` | `YES` / `NO`                       | `YES`               | Allows using FP16+INT8 mixed precision mode, so non-quantized parts of a model will be executed in FP16 precision for FP16 IR. Does not affect quantized FP32 IRs |