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
If you plan to develop with TorchServe and change some source code, you must install it from source code.
62
51
63
-
Ensure that you have `python3` installed, and the user has access to the site-packages or `~/.local/bin` is added to the `PATH` environment variable.
52
+
1. Clone the repository, including third-party modules, with `git clone --recurse-submodules --remote-submodules [email protected]:pytorch/serve.git`
53
+
2. Ensure that you have `python3` installed, and the user has access to the site-packages or `~/.local/bin` is added to the `PATH` environment variable.
54
+
3. Run the following script from the top of the source directory. NOTE: This script force re-installs `torchserve`, `torch-model-archiver` and `torch-workflow-archiver`if existing installations are found
64
55
65
-
Run the following script from the top of the source directory.
56
+
#### For Debian Based Systems/MacOS
66
57
67
-
NOTE: This script force re-installs `torchserve`, `torch-model-archiver` and `torch-workflow-archiver`if existing installations are found
Use `--cuda` flag with `install_dependencies.py`for installing cuda version specific dependencies. Possible values are `cu111`, `cu102`, `cu101`, `cu92`
69
+
For example `python ./ts_scripts/install_dependencies.py --environment=dev --rocm=rocm61`
77
70
78
-
#### For Windows
71
+
#### For Windows
79
72
80
-
Refer to the documentation [here](docs/torchserve_on_win_native.md).
73
+
Refer to the documentation [here](docs/torchserve_on_win_native.md).
81
74
82
-
For information about the model archiver, see [detailed documentation](model-archiver/README.md).
75
+
For information about the model archiver, see [detailed documentation](model-archiver/README.md).
0 commit comments