Skip to content

S
Serving

PaddlePaddle / Serving
大约 2 年 前同步成功

通知 187
Star 833
Fork 253
S
Serving
提交 fd0a85e4 编写于 作者: S ShiningZhang
浏览文件
操作

update SERVING_CONFIGURE.md&SERVING_CONFIGURE_CN.md with descrip of ir_optim

上级 78398965
显示空白变更内容
内联 并排
Showing with 6 addition and 6 deletion
doc/SERVING_CONFIGURE.md
浏览文件 @ fd0a85e4
...@@ -92,9 +92,9 @@ More flags: ...@@ -92,9 +92,9 @@ More flags:
| `mem_optim_off` | - | - | Disable memory / graphic memory optimization | | `mem_optim_off` | - | - | Disable memory / graphic memory optimization |
| `ir_optim` | bool | False | Enable analysis and optimization of calculation graph | | `ir_optim` | bool | False | Enable analysis and optimization of calculation graph |
| `use_mkl` (Only for cpu version) | - | - | Run inference with MKL | | `use_mkl` (Only for cpu version) | - | - | Run inference with MKL |
| `use_trt` (Only for trt version) | - | - | Run inference with TensorRT | | `use_trt` (Only for trt version) | - | - | Run inference with TensorRT. Need open with ir_optim. |
| `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. Need open with ir_optim. |
| `use_xpu` | - | - | Run PaddleLite inference with Baidu Kunlun XPU | | `use_xpu` | - | - | Run PaddleLite inference with Baidu Kunlun XPU. Need open with ir_optim. |
| `precision` | str | FP32 | Precision Mode, support FP32, FP16, INT8 | | `precision` | str | FP32 | Precision Mode, support FP32, FP16, INT8 |
| `use_calib` | bool | False | Use TRT int8 calibration | | `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 |
......
doc/SERVING_CONFIGURE_CN.md
浏览文件 @ fd0a85e4
...@@ -91,9 +91,9 @@ workdir_9393 ...@@ -91,9 +91,9 @@ workdir_9393
| `mem_optim_off` | - | - | Disable memory / graphic memory optimization | | `mem_optim_off` | - | - | Disable memory / graphic memory optimization |
| `ir_optim` | bool | False | Enable analysis and optimization of calculation graph | | `ir_optim` | bool | False | Enable analysis and optimization of calculation graph |
| `use_mkl` (Only for cpu version) | - | - | Run inference with MKL | | `use_mkl` (Only for cpu version) | - | - | Run inference with MKL |
| `use_trt` (Only for trt version) | - | - | Run inference with TensorRT | | `use_trt` (Only for trt version) | - | - | Run inference with TensorRT. Need open with ir_optim. |
| `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. Need open with ir_optim. |
| `use_xpu` | - | - | Run PaddleLite inference with Baidu Kunlun XPU | | `use_xpu` | - | - | Run PaddleLite inference with Baidu Kunlun XPU. Need open with ir_optim. |
| `precision` | str | FP32 | Precision Mode, support FP32, FP16, INT8 | | `precision` | str | FP32 | Precision Mode, support FP32, FP16, INT8 |
| `use_calib` | bool | False | Use TRT int8 calibration | | `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 |
......
Markdown is supported
0% 或 .
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 或