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

[data/llm/docs] Initial draft of user guide for Data LLM APIs #50674

Merged
merged 6 commits into from
Feb 19, 2025

Conversation

richardliaw
Copy link
Contributor

@richardliaw richardliaw commented Feb 18, 2025

Why are these changes needed?

Adds user guide and link-ins for Ray Data documentation.

This is part of the #50639 thread of work.

This is based on #50494

cc @comaniac @gvspraveen @kouroshHakha

Related issue number

Checks

  • I've signed off every commit(by using the -s flag, i.e., git commit -s) in this PR.
  • I've run scripts/format.sh to lint the changes in this PR.
  • I've included any doc changes needed for https://docs.ray.io/en/master/.
    • I've added any new APIs to the API Reference. For example, if I added a
      method in Tune, I've added it in doc/source/tune/api/ under the
      corresponding .rst file.
  • I've made sure the tests are passing. Note that there might be a few flaky tests, see the recent failures at https://flakey-tests.ray.io/
  • Testing Strategy
    • Unit tests
    • Release tests
    • This PR is not tested :(

@richardliaw richardliaw changed the title [draft][data/llm/docs] Initial draft of user guide for LLM APIs [draft][data/llm/docs] Initial draft of user guide for Data LLM APIs Feb 18, 2025
Comment on lines 22 to 25
# FIXME(comaniac)
pip uninstall -y torch
pip install torch==2.5.1 --index-url https://download.pytorch.org/whl/cu121

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

remove

Comment on lines 57 to 82
Configure vLLM for LLM inference
--------------------------------

Use the `VLLMProcessorConfig` to configure the vLLM engine.

.. testcode::

from ray.data.llm import VLLMProcessorConfig

processor_config = VLLMProcessorConfig(
model="meta-llama/Llama-3.1-8B-Instruct",
...
)
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Question - What other tips should we add here about this

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Look at vllm docs for examples on setting good args too


from ray.data.llm import VLLMProcessorConfig

processor_config = VLLMProcessorConfig(
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this is small v - vLLMProcessorConfig

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

fixed

@@ -12,6 +12,9 @@ Offline batch inference is a process for generating model predictions on a fixed
:width: 650px
:align: center

.. note::
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Add an example for a custom evaluation pipeline, reading from huggingface etc

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I will add this later

@richardliaw richardliaw changed the title [draft][data/llm/docs] Initial draft of user guide for Data LLM APIs [data/llm/docs] Initial draft of user guide for Data LLM APIs Feb 18, 2025
@richardliaw richardliaw added the go add ONLY when ready to merge, run all tests label Feb 18, 2025
@richardliaw richardliaw marked this pull request as ready for review February 18, 2025 23:25
@richardliaw richardliaw requested a review from a team as a code owner February 18, 2025 23:25
Signed-off-by: Richard Liaw <[email protected]>
Copy link
Collaborator

@comaniac comaniac left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Fixed the examples. Otherwise LGTM

richardliaw and others added 4 commits February 18, 2025 16:23
Co-authored-by: Cody Yu <[email protected]>
Signed-off-by: Richard Liaw <[email protected]>
Co-authored-by: Cody Yu <[email protected]>
Signed-off-by: Richard Liaw <[email protected]>
Signed-off-by: Richard Liaw <[email protected]>
@richardliaw richardliaw enabled auto-merge (squash) February 19, 2025 00:40
Signed-off-by: Richard Liaw <[email protected]>
@github-actions github-actions bot disabled auto-merge February 19, 2025 01:44
@richardliaw richardliaw enabled auto-merge (squash) February 19, 2025 01:47
@richardliaw richardliaw merged commit 6aa079a into ray-project:master Feb 19, 2025
6 checks passed
400Ping pushed a commit to 400Ping/ray that referenced this pull request Feb 20, 2025
…oject#50674)

## Why are these changes needed?

Adds user guide and link-ins for Ray Data documentation.

This is part of the ray-project#50639 thread of work.

This is based on ray-project#50494

cc @comaniac @gvspraveen @kouroshHakha

## Related issue number

<!-- For example: "Closes ray-project#1234" -->

## Checks

- [ ] I've signed off every commit(by using the -s flag, i.e., `git
commit -s`) in this PR.
- [ ] I've run `scripts/format.sh` to lint the changes in this PR.
- [ ] I've included any doc changes needed for
https://docs.ray.io/en/master/.
- [ ] I've added any new APIs to the API Reference. For example, if I
added a
method in Tune, I've added it in `doc/source/tune/api/` under the
           corresponding `.rst` file.
- [ ] I've made sure the tests are passing. Note that there might be a
few flaky tests, see the recent failures at https://flakey-tests.ray.io/
- Testing Strategy
   - [ ] Unit tests
   - [ ] Release tests
   - [ ] This PR is not tested :(

---------

Signed-off-by: Richard Liaw <[email protected]>
Co-authored-by: Cody Yu <[email protected]>
Signed-off-by: 400Ping <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
go add ONLY when ready to merge, run all tests
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants