[Feature] Modify cpu_hpi thread num (#4313)

* modify cpu_hpi thread num

* modify cpu_hpi thread num

docs/pipeline_deploy/high_performance_inference.en.md

@@ -302,11 +302,11 @@ The available configuration items for `backend_config` vary for different backen
   </tr>
   <tr>
     <td><code>openvino</code></td>
-    <td><code>cpu_num_threads</code> (<code>int</code>): The number of logical processors used for CPU inference. The default is <code>8</code>.</td>
+    <td><code>cpu_num_threads</code> (<code>int</code>): The number of logical processors used for CPU inference. The default is <code>10</code>.</td>
   </tr>
   <tr>
     <td><code>onnxruntime</code></td>
-    <td><code>cpu_num_threads</code> (<code>int</code>): The number of parallel computation threads within the operator during CPU inference. The default is <code>8</code>.</td>
+    <td><code>cpu_num_threads</code> (<code>int</code>): The number of parallel computation threads within the operator during CPU inference. The default is <code>10</code>.</td>
   </tr>
   <tr>
     <td><code>tensorrt</code></td>

docs/pipeline_deploy/high_performance_inference.md

@@ -303,11 +303,11 @@ output = model.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/
   </tr>
   <tr>
     <td><code>openvino</code></td>
-    <td><code>cpu_num_threads</code>（<code>int</code>）：CPU 推理使用的逻辑处理器数量。默认为 <code>8</code>。</td>
+    <td><code>cpu_num_threads</code>（<code>int</code>）：CPU 推理使用的逻辑处理器数量。默认为 <code>10</code>。</td>
   </tr>
   <tr>
     <td><code>onnxruntime</code></td>
-    <td><code>cpu_num_threads</code>（<code>int</code>）：CPU 推理时算子内部的并行计算线程数。默认为 <code>8</code>。</td>
+    <td><code>cpu_num_threads</code>（<code>int</code>）：CPU 推理时算子内部的并行计算线程数。默认为 <code>10</code>。</td>
   </tr>
   <tr>
     <td><code>tensorrt</code></td>

paddlex/inference/utils/hpi.py

@@ -61,11 +61,11 @@ InferenceBackend: TypeAlias = Literal[
 
 
 class OpenVINOConfig(BaseModel):
-    cpu_num_threads: int = 8
+    cpu_num_threads: int = 10
 
 
 class ONNXRuntimeConfig(BaseModel):
-    cpu_num_threads: int = 8
+    cpu_num_threads: int = 10
 
 
 class TensorRTConfig(BaseModel):

paddlex/inference/utils/pp_option.py

@@ -137,7 +137,7 @@ class PaddlePredictorOption(object):
             "run_mode": get_default_run_mode(self.model_name, device_type),
             "device_type": device_type,
             "device_id": device_id,
-            "cpu_threads": 8,
+            "cpu_threads": 10,
             "delete_pass": [],
             "enable_new_ir": True if self.model_name not in NEWIR_BLOCKLIST else False,
             "enable_cinn": False,

paddlex/ops/__init__.py

@@ -72,7 +72,7 @@ class CustomOperatorPathFinder:
         return importlib.machinery.ModuleSpec(
             name=fullname,
             loader=CustomOperatorPathLoader(),
-            is_package=False,        
+            is_package=False,
         )