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

[Examples] vLLM example for SkyServe + Mixtral #2948

Merged
merged 4 commits into from
Jan 11, 2024
Merged

Conversation

cblmemo
Copy link
Collaborator

@cblmemo cblmemo commented Jan 6, 2024

Added example in #2922 to llm/vllm.

Tested (run the relevant ones):

  • Code formatting: bash format.sh
  • Any manual or new tests for this PR (please specify below)
  • All smoke tests: pytest tests/test_smoke.py
  • Relevant individual smoke tests: pytest tests/test_smoke.py::test_fill_in_the_name
  • Backward compatibility tests: bash tests/backward_comaptibility_tests.sh

@cblmemo cblmemo mentioned this pull request Jan 6, 2024
6 tasks
@@ -126,3 +126,61 @@ curl http://$IP:8000/v1/chat/completions \
}
}
```

## Serving Mixtral 8x7b model with vLLM and SkyServe
Copy link
Collaborator

@Michaelvll Michaelvll Jan 8, 2024

Choose a reason for hiding this comment

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

We already have the mixtral 8x7b + vLLM and SkyServe in llm/mixtral. Should we just make the example above to be launchable with sky serve and have an additional link refering to the llm/mixtral?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Make sense! Changed. PTAL again 🫡

Copy link
Collaborator

@Michaelvll Michaelvll left a comment

Choose a reason for hiding this comment

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

Thanks for updating the example @cblmemo! Left several comments.

llm/vllm/README.md Outdated Show resolved Hide resolved
llm/vllm/README.md Outdated Show resolved Hide resolved
llm/vllm/README.md Outdated Show resolved Hide resolved
llm/vllm/README.md Outdated Show resolved Hide resolved
llm/vllm/README.md Outdated Show resolved Hide resolved
HF_TOKEN: <your-huggingface-token> # Change to your own huggingface token

resources:
accelerators: L4:1
Copy link
Collaborator

Choose a reason for hiding this comment

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

Let's use multiple accelerators for this and the original yaml files, so that a user without GCP credentials can use the yaml out-of-the-box, e.g.,{L4:1, A10G:1, A10:1, A100:1, A100-80GB:1}

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Done. Thanks!

cblmemo and others added 2 commits January 11, 2024 10:43
Co-authored-by: Zhanghao Wu <zhanghao.wu@outlook.com>
@cblmemo cblmemo merged commit 7ac091f into master Jan 11, 2024
19 checks passed
@cblmemo cblmemo deleted the vllm-mixtral-example branch January 11, 2024 03:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants