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

[Bugfix] Handle <|tool_call|> token in granite tool parser #11039

Merged

Conversation

tjohnson31415
Copy link
Contributor

@tjohnson31415 tjohnson31415 commented Dec 9, 2024

Small tweak to the granite tool parser to support handle the <|tool_call|> token that can be generated, eg.

<|start of role|>user<|end of role|>What is temperature in Boston?<|end of text|>
<|start of role|>assistant<|end of role|><|tool call|>[{“name”: “get temp”, ...}]<|end of text|>
<|start of role|>tool response<|end of role|>{“temp”: 20.5, “unit”: “C”}<|end of text|>

REF: Table 3 on page 14 in https://github.com/ibm-granite/granite-3.0-language-models/blob/main/paper.pdf

Supporting this matters if the request has skip_special_tokens=False. Currently, the parser will not parse out the tool call when the output starts with <|tool_call|>.

I have also noticed interesting behavior between the granite model and llama w.r.t handling the tool call special token. With meta-llama/Llama-3.1-8B-Instruct, including skip_special_tokens=True on the vLLM request does not skip generation of the <|python_tag|> special token.

cc: @maxdebayser

Copy link

github-actions bot commented Dec 9, 2024

👋 Hi! Thank you for contributing to the vLLM project.
Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can do one of these:

  • Add ready label to the PR
  • Enable auto-merge.

🚀

@mergify mergify bot added the frontend label Dec 9, 2024
Copy link
Member

@DarkLight1337 DarkLight1337 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 fixing!

@DarkLight1337 DarkLight1337 changed the title fix: handle <|tool_call|> token in granite tool parser [Bugfix] Handle <|tool_call|> token in granite tool parser Dec 10, 2024
@DarkLight1337 DarkLight1337 enabled auto-merge (squash) December 10, 2024 04:42
@github-actions github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label Dec 10, 2024
@DarkLight1337 DarkLight1337 merged commit beb16b2 into vllm-project:main Dec 10, 2024
64 of 65 checks passed
@tjohnson31415 tjohnson31415 deleted the granite-tool-call-token branch December 10, 2024 17:18
sleepwalker2017 pushed a commit to sleepwalker2017/vllm that referenced this pull request Dec 13, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
frontend ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants