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
* Refactor Dokcerfile.cpp
* Update documentation
* Use nvidia devel image instead of runtime image
* Configure timezone and enable DEBIAN_FRONTEND=noninteractive
* Include documentation about dev container behavior
Copy file name to clipboardexpand all lines: cpp/README.md
+3-2
Original file line number
Diff line number
Diff line change
@@ -2,10 +2,10 @@
2
2
## Requirements
3
3
* C++17
4
4
* GCC version: gcc-9
5
-
* cmake version: 3.18+
5
+
* cmake version: 3.26.4+
6
6
* Linux
7
7
8
-
For convenience, a docker container can be used as the development environment to build and install Torchserve CPP
8
+
For convenience, a [docker container](../docker/README.md#create-torchserve-docker-image) can be used as the development environment to build and install Torchserve CPP
9
9
```
10
10
cd serve/docker
11
11
# For CPU support
@@ -21,6 +21,7 @@ docker run [-v /path/to/build/dir:/serve/cpp/_build] -it pytorch/torchserve:cpp-
21
21
# For GPU support
22
22
docker run --gpus all [-v /path/to/build/dir:/serve/cpp/_build] -it pytorch/torchserve:cpp-dev-gpu /bin/bash
23
23
```
24
+
`Warning`: The dev docker container does not install all necessary dependencies or build Torchserve CPP. Please follow the steps below after starting the container.
24
25
25
26
## Installation and Running TorchServe CPP
26
27
This installation instruction assumes that TorchServe is already installed through pip/conda/source. If this is not the case install it after the `Install dependencies` step through your preferred method.
0 commit comments