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

Fix crash when special tokens aren't found in model config. #60

Merged
merged 2 commits into from
Jan 16, 2025

Conversation

maxdebayser
Copy link
Contributor

Some models such as sentence-transformers/all-MiniLM-L12-v2 don't have special tokens such as "bos_token" in their tokenizer configuration. This causes a key error when the warmup logic tries to get the id for these tokens. However, since the IDs are only used to exclude them from the set of tokens that can be generated during the warmup, it doesn't make a difference if they don't exist.

@maxdebayser maxdebayser requested a review from tdoublep January 16, 2025 01:03
Copy link

👋 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.

🚀

Copy link
Member

@tdoublep tdoublep left a comment

Choose a reason for hiding this comment

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

LGTM

@maxdebayser maxdebayser merged commit 590042e into main Jan 16, 2025
9 of 10 checks passed
@maxdebayser maxdebayser deleted the fix_special_tokens branch January 16, 2025 13:16
tdoublep pushed a commit that referenced this pull request Jan 20, 2025
This PR applies lint checks to the repository as done in the upstream
vLLM repository.

### Changes:

- removed unused imports with autoflake: `autoflake
--remove-all-unused-imports --in-place <file>`
- applied lint check to the current repo (`bash format.sh`)
- added files for automatic link check for PRs to the `main` branch of
our internal fork (added 4 files to `.github/workflows`)

The code has been tested in client/server mode for the `llama 194m` and
`granite 3b` on `AIU` and `CPU`.
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.

2 participants