Skip to content

Conversation

@Kacper-Pietkun
Copy link
Contributor

@Kacper-Pietkun Kacper-Pietkun commented Nov 18, 2025

Sleep mode level 1 - based on HabanaAI/vllm-fork#2055

Copilot AI review requested due to automatic review settings November 18, 2025 11:42
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

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

Pull Request Overview

This PR implements sleep mode support for HPU workers in vLLM, enabling memory reduction by moving models to CPU and clearing KV cache when workers are idle.

  • Adds sleep() and wake_up() methods to HPUWorker class for memory management
  • Enables sleep mode availability on the HPU platform
  • Reorganizes import statements for better code organization

Reviewed Changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 4 comments.

File Description
vllm_gaudi/v1/worker/hpu_worker.py Implements sleep/wake_up methods with model CPU offloading and KV cache management, adds state tracking flags
vllm_gaudi/platform.py Declares sleep mode support available on HPU platform

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

@github-actions
Copy link

🚧 CI Blocked

The main CI workflow was not started for the following reason:

This is a Draft PR. Please mark it as 'Ready for Review' to trigger the CI.

@Kacper-Pietkun Kacper-Pietkun force-pushed the dev/kpietkun/sleep_mode branch from 1a94591 to d6922a2 Compare November 19, 2025 11:34
@github-actions
Copy link

🚧 CI Blocked

The main CI workflow was not started for the following reason:

This is a Draft PR. Please mark it as 'Ready for Review' to trigger the CI.

@Kacper-Pietkun Kacper-Pietkun force-pushed the dev/kpietkun/sleep_mode branch from d6922a2 to 2d629d0 Compare November 21, 2025 15:26
@github-actions
Copy link

🚧 CI Blocked

The main CI workflow was not started for the following reason:

This is a Draft PR. Please mark it as 'Ready for Review' to trigger the CI.

Signed-off-by: Kacper Pietkun <[email protected]>
@Kacper-Pietkun Kacper-Pietkun force-pushed the dev/kpietkun/sleep_mode branch from 2d629d0 to 43c9d88 Compare November 24, 2025 09:44
@github-actions
Copy link

🚧 CI Blocked

The main CI workflow was not started for the following reason:

This is a Draft PR. Please mark it as 'Ready for Review' to trigger the CI.

Signed-off-by: Kacper Pietkun <[email protected]>
@github-actions
Copy link

🚧 CI Blocked

The main CI workflow was not started for the following reason:

This is a Draft PR. Please mark it as 'Ready for Review' to trigger the CI.

@github-actions
Copy link

🚧 CI Blocked

The main CI workflow was not started for the following reason:

This is a Draft PR. Please mark it as 'Ready for Review' to trigger the CI.

@Kacper-Pietkun
Copy link
Contributor Author

/run-gaudi-tests

Signed-off-by: Kacper Pietkun <[email protected]>
@Kacper-Pietkun
Copy link
Contributor Author

/run-gaudi-tests

@github-actions
Copy link

✅ CI Passed

All checks passed successfully against the following vllm commit:
e924bbb4f4ac3258a71a18ac4c753c8056bc059f

@Kacper-Pietkun
Copy link
Contributor Author

/run-gaudi-tests

1 similar comment
@Kacper-Pietkun
Copy link
Contributor Author

/run-gaudi-tests

@github-actions
Copy link

github-actions bot commented Dec 1, 2025

✅ CI Passed

All checks passed successfully against the following vllm commit:
0353d2e162cbda776d9dbfe026e65303204a7f1f

Signed-off-by: Kacper Pietkun <[email protected]>
@Kacper-Pietkun Kacper-Pietkun force-pushed the dev/kpietkun/sleep_mode branch from c8969d7 to 2314cce Compare December 2, 2025 05:14
@github-actions
Copy link

github-actions bot commented Dec 2, 2025

🚧 CI Blocked

The main CI workflow was not started for the following reason:

Your branch is behind the base branch. Please merge or rebase to get the latest changes.

@Kacper-Pietkun
Copy link
Contributor Author

/run-gaudi-tests

@Kacper-Pietkun Kacper-Pietkun force-pushed the dev/kpietkun/sleep_mode branch from 007dc3d to 2314cce Compare December 2, 2025 05:43
@github-actions
Copy link

github-actions bot commented Dec 2, 2025

🚧 CI Blocked

The main CI workflow was not started for the following reason:

Your branch is behind the base branch. Please merge or rebase to get the latest changes.

@Kacper-Pietkun
Copy link
Contributor Author

/run-gaudi-tests

Signed-off-by: Kacper Pietkun <[email protected]>
@Kacper-Pietkun Kacper-Pietkun force-pushed the dev/kpietkun/sleep_mode branch from c930e9c to 8f10fcd Compare December 2, 2025 05:46
@Kacper-Pietkun
Copy link
Contributor Author

/run-gaudi-tests

@github-actions
Copy link

github-actions bot commented Dec 2, 2025

✅ CI Passed

All checks passed successfully against the following vllm commit:
0353d2e162cbda776d9dbfe026e65303204a7f1f

exit -1
fi
echo "Test with sleep mode passed"

Copy link
Collaborator

Choose a reason for hiding this comment

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

Hi, @Kacper-Pietkun , may you move it to ci_gsm8k_tests.sh => Sorry for the very confusing name, but only funcs inside ci_gsm8k_tests.sh will be auto detected by our CI

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Sure, done

Signed-off-by: Kacper Pietkun <[email protected]>
@github-actions
Copy link

github-actions bot commented Dec 4, 2025

🚧 CI Blocked

The main CI workflow was not started for the following reason:

Your branch is behind the base branch. Please merge or rebase to get the latest changes.

@github-actions
Copy link

github-actions bot commented Dec 4, 2025

✅ CI Passed

All checks passed successfully against the following vllm commit:
5f91cdda75b24a3d9cdda8c82897db07b288b5c9

@xuechendi xuechendi merged commit a955e1e into vllm-project:main Dec 4, 2025
45 checks passed
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