-
Notifications
You must be signed in to change notification settings - Fork 6.7k
[Doc] Added ray-serve llm doc #52832
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
Conversation
Can you fix the CI error? In addition, each commit needs to commit with |
1ff1edc
to
b49a3e0
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks a lot for contributing this, it looks good to me. Before merging this, we first need to merge ray-project/kuberay#3517 :)
@kevin85421 Can you drive that PR forward?
Signed-off-by: DPatel_7 <dpatel@gocommotion.com>
Signed-off-by: DPatel_7 <dpatel@gocommotion.com>
Signed-off-by: DPatel_7 <dpatel@gocommotion.com>
made updates. @kevin85421 |
Signed-off-by: DPatel_7 <dpatel@gocommotion.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Would you mind verifying whether the YAML (ray-project/kuberay#3517 (review)) still works or not? This doc has removed the step of creating a namespace, but the YAML still uses the namespace.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Taking a closer look this afternoon; might push some edits
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
@kevin85421 Ready to merge when green |
Co-authored-by: angelinalg <122562471+angelinalg@users.noreply.github.com> Co-authored-by: Kai-Hsun Chen <kaihsun@apache.org> Signed-off-by: Seiji Eicher <58963096+eicherseiji@users.noreply.github.com>
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks great!
For additional security, instead of passing the HF Access Token directly as an environment variable, create a Kubernetes Secret containing your Hugging Face access token. Download the Ray Serve LLM service config .yaml file using the following command: | ||
|
||
```sh | ||
curl -o ray-service.llm-serve.yaml https://raw.githubusercontent.com/ray-project/kuberay/master/ray-operator/config/samples/ray-service.llm-serve.yaml |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We can use the release branch https://github.com/ray-project/kuberay/tree/release-1.4.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Seems like ray-project/kuberay#3517 needs to be cherry-picked
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Just have some style nits. I'd appreciate you fixing prior to merge to decrease tech debt. Thanks!
Co-authored-by: angelinalg <122562471+angelinalg@users.noreply.github.com> Signed-off-by: Seiji Eicher <58963096+eicherseiji@users.noreply.github.com>
Add example of serving a Large Language Model using Ray Serve LLM on Kubernetes Signed-off-by: DPatel_7 <dpatel@gocommotion.com> Signed-off-by: Seiji Eicher <seiji@anyscale.com> Signed-off-by: Seiji Eicher <58963096+eicherseiji@users.noreply.github.com> Co-authored-by: DPatel_7 <dpatel@gocommotion.com> Co-authored-by: Seiji Eicher <seiji@anyscale.com> Co-authored-by: Seiji Eicher <58963096+eicherseiji@users.noreply.github.com> Co-authored-by: angelinalg <122562471+angelinalg@users.noreply.github.com> Co-authored-by: Kai-Hsun Chen <kaihsun@apache.org> Signed-off-by: elliot-barn <elliot.barnwell@anyscale.com>
Add example of serving a Large Language Model using Ray Serve LLM on Kubernetes Signed-off-by: DPatel_7 <dpatel@gocommotion.com> Signed-off-by: Seiji Eicher <seiji@anyscale.com> Signed-off-by: Seiji Eicher <58963096+eicherseiji@users.noreply.github.com> Co-authored-by: DPatel_7 <dpatel@gocommotion.com> Co-authored-by: Seiji Eicher <seiji@anyscale.com> Co-authored-by: Seiji Eicher <58963096+eicherseiji@users.noreply.github.com> Co-authored-by: angelinalg <122562471+angelinalg@users.noreply.github.com> Co-authored-by: Kai-Hsun Chen <kaihsun@apache.org> Signed-off-by: elliot-barn <elliot.barnwell@anyscale.com>
Why are these changes needed?
Add example of serving a Large Language Model using Ray Serve LLM on Kubernetes
Related issue number
Checks
git commit -s
) in this PR.scripts/format.sh
to lint the changes in this PR.method in Tune, I've added it in
doc/source/tune/api/
under thecorresponding
.rst
file.