Skip to content

Commit d28cb65

Browse files
committed
Add note about libnvinfer packages being optional.
1 parent 35deba9 commit d28cb65

File tree

1 file changed

+3
-1
lines changed

1 file changed

+3
-1
lines changed

site/en/install/gpu.md

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -67,7 +67,7 @@ The following NVIDIA® software must be installed on your system:
6767
* [cuDNN SDK 8.1.0](https://developer.nvidia.com/cudnn){:.external}
6868
[cuDNN versions](https://developer.nvidia.com/rdp/cudnn-archive){:.external}).
6969
* *(Optional)*
70-
[TensorRT 7](https://docs.nvidia.com/deeplearning/tensorrt/archives/index.html#trt_7){:.external}
70+
[TensorRT](https://docs.nvidia.com/deeplearning/tensorrt/archives/index.html#trt_7){:.external}
7171
to improve latency and throughput for inference on some models.
7272

7373
## Linux setup
@@ -104,6 +104,7 @@ complicates installation of the NVIDIA driver and is beyond the scope of these i
104104
<code class="devsite-terminal">sudo apt-get update</code>
105105

106106
# Install development and runtime libraries (~4GB)
107+
# libnvinfer packages are optional, needed to support TensorRT inference.
107108
<code class="devsite-terminal">sudo apt-get install --no-install-recommends \
108109
cuda-11-2 \
109110
libcudnn8=8.1.0.77-1+cuda11.2 \
@@ -128,6 +129,7 @@ complicates installation of the NVIDIA driver and is beyond the scope of these i
128129
<code class="devsite-terminal">sudo apt-get update</code>
129130

130131
# Install development and runtime libraries (~4GB)
132+
# libnvinfer packages are optional, needed to support TensorRT inference.
131133
<code class="devsite-terminal">sudo apt-get install --no-install-recommends \
132134
cuda-11-2 \
133135
libcudnn8=8.1.0.77-1+cuda11.2 \

0 commit comments

Comments
 (0)