Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update mentions of Python 3.8 -> 3.10 #253

Merged
merged 1 commit into from
Jun 2, 2023
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -582,13 +582,13 @@ documentation.
## Managing Python Runtime and Libraries

Python backend shipped in the [NVIDIA GPU Cloud](https://ngc.nvidia.com/)
containers uses Python 3.8. Python backend is able to use the libaries
containers uses Python 3.10. Python backend is able to use the libaries
that exist in the current Python environment. These libraries can
be installed in a virtualenv, conda environment, or the global system
Python. These libraries will only be used if the Python version matches
the Python version of the Python backend's stub executable. For example,
if you install a set of libraries in a Python 3.9 environment and your
Python backend stub is compiled with Python 3.8 these libraries will NOT
Python backend stub is compiled with Python 3.10 these libraries will NOT
be available in your Python model served using Triton. You would need to
compile the stub executble with Python 3.9 using the instructions in
[Building Custom Python Backend Stub](#building-custom-python-backend-stub)
Expand All @@ -597,7 +597,7 @@ section.
### Building Custom Python Backend Stub

**Important Note: You only need to compile a custom Python backend stub if the
Python version is different from Python 3.8 which is shipped by
Python version is different from Python 3.10 which is shipped by
default in the Triton containers.**

Python backend uses a *stub* process to connect your `model.py` file to the
Expand Down Expand Up @@ -759,7 +759,7 @@ In this case you only need to pack your environment using `conda-pack` and
provide the path to tar file in the model config. However, the previous note
still applies here and the version of the Python interpreter inside the conda
environment must match the Python version of stub used by Python backend. The
default version of the stub is Python 3.8.
default version of the stub is Python 3.10.

3. You can share a single execution environment across multiple models. You
need to provide the path to the tar file in the `EXECUTION_ENV_PATH` in the
Expand Down