You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@@ -75,19 +77,21 @@ If you installed Python via Homebrew or the Python website, `pip` was installed
75
77
76
78
* If your computer has NVIDIA® GPU, please make sure that the following conditions are met and install [the GPU Version of PaddlePaddle](#gpu)
77
79
78
-
* **CUDA toolkit 10.1/10.2 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher)**
80
+
* **CUDA toolkit 10.1 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher)**
79
81
80
-
* **CUDA toolkit 11.1 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher)**
82
+
* **CUDA toolkit 10.2 with cuDNN 7 (cuDNN version>=7.6.5, for multi card support, NCCL2.7 or higher;for PaddleTensorRT deployment, TensorRT7.0.0.11)**
81
83
82
-
* **CUDA toolkit 11.2 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher)**
84
+
* **CUDA toolkit 11.1 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher;for PaddleTensorRT deployment, TensorRT7.2.3.4)**
83
85
84
-
* **CUDA toolkit 11.6 with cuDNN v8.4.0(for multi card support, NCCL2.7 or higher)**
86
+
* **CUDA toolkit 11.2 with cuDNN v8.1.1(for multi card support, NCCL2.7 or higher;for PaddleTensorRT deployment, TensorRT8.0.3.4)**
85
87
86
-
* **CUDA toolkit 11.7 with cuDNN v8.4.1(for multi card support, NCCL2.7 or higher)**
88
+
* **CUDA toolkit 11.6 with cuDNN v8.4.0(for multi card support, NCCL2.7 or higher;for PaddleTensorRT deployment, TensorRT8.4.0.6)**
89
+
90
+
* **CUDA toolkit 11.7 with cuDNN v8.4.1(for multi card support, NCCL2.7 or higher;for PaddleTensorRT deployment, TensorRT8.4.2.4)**
87
91
88
92
* **Hardware devices with GPU computing power over 3.5**
89
93
90
-
You can refer to NVIDIA official documents for installation process and configuration method of CUDA and cudnn. Please refer to [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/),[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/)
94
+
You can refer to NVIDIA official documents for installation process and configuration method of CUDA and cudnn. Please refer to [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/),[cuDNN](https://docs.nvidia.com/deeplearning/sdk/cudnn-install/),[TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download)
91
95
92
96
* If you need to use a multi-card environment, please make sure that you have installed nccl2 correctly, or install nccl2 according to the following instructions (here are the installation instructions of nccl2 under CUDA10.2 and cuDNN7. For more version installation information, please refer to NVIDIA [Official Website](https://developer.nvidia.com/nccl)):
93
97
@@ -133,7 +137,7 @@ You can choose the following version of PaddlePaddle to start installation:
To determine whether your machine supports `avx`, you can use the following command. If the output contains `avx`, it means that the machine supports `avx`:
@@ -237,10 +234,10 @@ Note:
237
234
* If you want to install the Paddle package with `avx` and `openblas`, you can use the following command to download the wheel package to the local, and then use `python -m pip install [name].whl` to install locally ([name] is the name of the wheel package):
* If you want to get better deployment performance by using PaddleTensorRT for CUDA11.2, you can [download the Paddle package compiled with cuDNN8.2.1 and TensorRT8.0.3.4.](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html)
0 commit comments