提交 072114e7 编写于 作者: S ShiningZhang

update description of use_calib in README

上级 b631ff0a
...@@ -188,7 +188,7 @@ python3 -m paddle_serving_server.serve --model uci_housing_model --thread 10 --p ...@@ -188,7 +188,7 @@ python3 -m paddle_serving_server.serve --model uci_housing_model --thread 10 --p
| `use_lite` (Only for Intel x86 CPU or ARM CPU) | - | - | Run PaddleLite inference | | `use_lite` (Only for Intel x86 CPU or ARM CPU) | - | - | Run PaddleLite inference |
| `use_xpu` | - | - | Run PaddleLite inference with Baidu Kunlun XPU | | `use_xpu` | - | - | Run PaddleLite inference with Baidu Kunlun XPU |
| `precision` | str | FP32 | Precision Mode, support FP32, FP16, INT8 | | `precision` | str | FP32 | Precision Mode, support FP32, FP16, INT8 |
| `use_calib` | bool | False | Only for deployment with TensorRT | | `use_calib` | bool | False | Use TRT int8 calibration |
| `gpu_multi_stream` | bool | False | EnableGpuMultiStream to get larger QPS | | `gpu_multi_stream` | bool | False | EnableGpuMultiStream to get larger QPS |
#### Description of asynchronous model #### Description of asynchronous model
......
...@@ -187,7 +187,7 @@ python3 -m paddle_serving_server.serve --model uci_housing_model --thread 10 --p ...@@ -187,7 +187,7 @@ python3 -m paddle_serving_server.serve --model uci_housing_model --thread 10 --p
| `use_lite` (Only for Intel x86 CPU or ARM CPU) | - | - | Run PaddleLite inference | | `use_lite` (Only for Intel x86 CPU or ARM CPU) | - | - | Run PaddleLite inference |
| `use_xpu` | - | - | Run PaddleLite inference with Baidu Kunlun XPU | | `use_xpu` | - | - | Run PaddleLite inference with Baidu Kunlun XPU |
| `precision` | str | FP32 | Precision Mode, support FP32, FP16, INT8 | | `precision` | str | FP32 | Precision Mode, support FP32, FP16, INT8 |
| `use_calib` | bool | False | Only for deployment with TensorRT | | `use_calib` | bool | False | Use TRT int8 calibration |
| `gpu_multi_stream` | bool | False | EnableGpuMultiStream to get larger QPS | | `gpu_multi_stream` | bool | False | EnableGpuMultiStream to get larger QPS |
#### 异步模型的说明 #### 异步模型的说明
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册