File tree Expand file tree Collapse file tree 1 file changed +3
-1
lines changed Expand file tree Collapse file tree 1 file changed +3
-1
lines changed Original file line number Diff line number Diff line change @@ -67,7 +67,7 @@ The following NVIDIA® software must be installed on your system:
67
67
* [ cuDNN SDK 8.1.0] ( https://developer.nvidia.com/cudnn ) {:.external}
68
68
[ cuDNN versions] ( https://developer.nvidia.com/rdp/cudnn-archive ) {:.external}).
69
69
* * (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}
71
71
to improve latency and throughput for inference on some models.
72
72
73
73
## Linux setup
@@ -104,6 +104,7 @@ complicates installation of the NVIDIA driver and is beyond the scope of these i
104
104
<code class =" devsite-terminal " >sudo apt-get update</code >
105
105
106
106
# Install development and runtime libraries (~4GB)
107
+ # libnvinfer packages are optional, needed to support TensorRT inference.
107
108
<code class =" devsite-terminal " >sudo apt-get install --no-install-recommends \
108
109
cuda-11-2 \
109
110
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
128
129
<code class =" devsite-terminal " >sudo apt-get update</code >
129
130
130
131
# Install development and runtime libraries (~4GB)
132
+ # libnvinfer packages are optional, needed to support TensorRT inference.
131
133
<code class =" devsite-terminal " >sudo apt-get install --no-install-recommends \
132
134
cuda-11-2 \
133
135
libcudnn8=8.1.0.77-1+cuda11.2 \
You can’t perform that action at this time.
0 commit comments