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.

Sign up for GitHub

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

Jump to bottom

[Model] Support is_causal HF config field for Qwen2 model #10621

Merged
merged 4 commits into from
Nov 25, 2024
Merged

[Model] Support is_causal HF config field for Qwen2 model #10621

merged 4 commits into from
Nov 25, 2024

Conversation

DarkLight1337
Copy link
Member

@github-actions GitHub Actions
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.

🚀

@mergify mergify bot added the documentation Improvements or additions to documentation label Nov 25, 2024
@DarkLight1337
Copy link
Member Author

Let me verify that the test passes first before adding ready label.

@DarkLight1337
Copy link
Member Author

Oh, this is awkward. By default HF assigns is_decoder=False for all models, even the text generation models.

@DarkLight1337
Copy link
Member Author

Maybe I have to use another config field for this...

@DarkLight1337
Use is_causal field instead
6b448f8 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337 DarkLight1337 changed the title [Model] Support is_decoder HF config for Qwen2 model [Model] Support is_causal HF config field for Qwen2 model Nov 25, 2024
@DarkLight1337
Make debugging easier
21df44f 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337 DarkLight1337 added the ready ONLY add when PR is ready to merge/full CI is needed label Nov 25, 2024
@DarkLight1337 DarkLight1337 enabled auto-merge (squash) November 25, 2024 07:50
@DarkLight1337
Copy link
Member Author

Using is_causal passes the tests locally.

@DarkLight1337
Reword
a0b769c 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337 DarkLight1337 merged commit ed46f14 into vllm-project:main Nov 25, 2024
51 checks passed
@DarkLight1337 DarkLight1337 deleted the qwen2-is-decoder branch November 25, 2024 10:22
@DarkLight1337 DarkLight1337 mentioned this pull request Nov 25, 2024
Merged
afeldman-nm pushed a commit to neuralmagic/vllm that referenced this pull request Dec 2, 2024
@DarkLight1337 @afeldman-nm
[Model] Support is_causal HF config field for Qwen2 model (vllm-pro…
930f2cc 
…ject#10621)

Signed-off-by: DarkLight1337 <[email protected]>
Signed-off-by: Andrew Feldman <[email protected]>
sleepwalker2017 pushed a commit to sleepwalker2017/vllm that referenced this pull request Dec 13, 2024
@DarkLight1337
[Model] Support is_causal HF config field for Qwen2 model (vllm-pro…
42af491 
…ject#10621)

Signed-off-by: DarkLight1337 <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@youkaichao youkaichao youkaichao approved these changes

@ywang96 ywang96 Awaiting requested review from ywang96 ywang96 is a code owner

Assignees
No one assigned
Labels
documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@DarkLight1337 @youkaichao