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

[BugFix] fix wrong output when using lora and num_scheduler_steps=8 #11161

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

[BugFix] fix wrong output when using lora and num_scheduler_steps=8 #11161

wants to merge 2 commits into from

Conversation

sleepwalker2017
Copy link

FIX issue #9688 #11086

@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.

🚀

@sleepwalker2017
Copy link
Author

sleepwalker2017 commented Dec 13, 2024 •
edited
Loading

@jeejeelee Hi, I've sent a new pr, please help check it.

The dummy lora modules are not cleared when using multi-step runner. so the real loras are never loaded. that leads to the wrong result.

jeejeelee
jeejeelee requested changes Dec 13, 2024
View reviewed changes
Copy link
Collaborator

@jeejeelee jeejeelee left a comment

Choose a reason for hiding this comment

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

Could you plz add unit test for this，maybe test_llama_tp is a good choice

vllm/worker/worker.py
@@ -252,9 +252,6 @@ def determine_num_available_blocks(self) -> Tuple[int, int]:
available_kv_cache_memory / (1024**3),
self.cache_config.gpu_memory_utilization)

# Final cleanup
if self.model_runner.lora_manager:
Copy link
Collaborator

Choose a reason for hiding this comment

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

We should keep this comment.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@jeejeelee jeejeelee jeejeelee requested changes

@zhuohan123 zhuohan123 Awaiting requested review from zhuohan123 zhuohan123 is a code owner

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

@alexm-redhat alexm-redhat Awaiting requested review from alexm-redhat alexm-redhat is a code owner

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

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

Requested changes must be addressed to merge this pull request.

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@sleepwalker2017 @jeejeelee