-
Notifications
You must be signed in to change notification settings - Fork 77
UX fix: hide warmup logs #539
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
Conversation
Signed-off-by: Agata Dobrzyniewicz <adobrzyniewicz@habana.ai>
Signed-off-by: Agata Dobrzyniewicz <adobrzyniewicz@habana.ai>
Signed-off-by: Agata Dobrzyniewicz <adobrzyniewicz@habana.ai>
🚧 CI BlockedThe main CI workflow was not started for the following reason:
|
There was a problem hiding this 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 improves the user experience during model warmup by hiding verbose logs behind a developer flag and adding progress bars. When VLLM_ENABLE_EXPERIMENTAL_FLAGS is disabled (default), users see only progress bars. Enabling the flag restores detailed logging for developers. The PR also removes the deprecated VLLM_USE_V1 flag and reclassifies user flags as no longer experimental.
Key changes:
- Warmup logs now hidden by default, replaced with tqdm progress bars
VLLM_USE_V1flag removed from user flags- User flags excluded from experimental flags list
Reviewed Changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| vllm_gaudi/v1/worker/hpu_model_runner.py | Adds tqdm progress bars for warmup phases and gates detailed logging behind VLLM_ENABLE_EXPERIMENTAL_FLAGS |
| vllm_gaudi/extension/runtime.py | Filters user flags out of experimental flags list to prevent duplicate categorization |
| vllm_gaudi/extension/features.py | Removes deprecated VLLM_USE_V1 flag from user flags list |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Signed-off-by: Agata Dobrzyniewicz <adobrzyniewicz@habana.ai>
🚧 CI BlockedThe main CI workflow was not started for the following reason:
|
✅ CI PassedAll checks passed successfully against the following vllm commit: |
✅ CI PassedAll checks passed successfully against the following vllm commit: |
✅ CI PassedAll checks passed successfully against the following vllm commit: |
Signed-off-by: Agata Dobrzyniewicz <adobrzyniewicz@habana.ai>
| | `VLLM_EXPONENTIAL_BUCKETING` | Enables exponential bucket spacing instead of linear spacing. | `true` | | ||
| | `VLLM_BUCKETING_FROM_FILE` | Enables reading bucket configuration from file | `None` | | ||
|
|
||
| ## Experimental Parameters |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There is mention of "Experimenta" still in the code:
| "From v0.12.0 release using those flags without VLLM_ENABLE_EXPERIMENTAL_FLAGS will trigger a fatal error.") |
should it be renamed?
✅ CI PassedAll checks passed successfully against the following vllm commit: |
If VLLM_ENABLE_EXPERIMENTAL_FLAGS is set to 0 or not set warmup will stay hidden with only progress bar.
Enabling this flag will bring back old logs
Additionally remove VLLM_USE_V1 flag
Additionally all user flags are no longer experimental