Open
Conversation
yenuo26
reviewed
Mar 26, 2026
| if "audio_ttfp" in goodput_config_dict: | ||
| valid_metrics.append(audio_ttfps) | ||
| slo_values.append(goodput_config_dict["audio_ttft"] / MILLISECONDS_TO_SECONDS_CONVERSION) | ||
| slo_values.append(goodput_config_dict["audio_ttfp"] / MILLISECONDS_TO_SECONDS_CONVERSION) |
Contributor
There was a problem hiding this comment.
Maybe we can add UT for this feature?
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED.
Purpose
Fix : #1872
Changes
1. Fix goodput
audio_ttfpmetric key typoFile:
vllm_omni/benchmarks/metrics/metrics.pyThe goodput calculation was reading
audio_ttftinstead ofaudio_ttfp, causing the audio first-packet latency SLO to be silently ignored.Changed
"audio_ttft"→"audio_ttfp"in the goodput config lookup.2. Add
audio_durationto CLI--percentile-metricshelpFile:
vllm_omni/entrypoints/cli/benchmark/serve.pyvllm bench serve --helpwas missingaudio_durationin the--percentile-metricshelp text, even though the implementation supports it.Updated help string to include
"audio_ttfp", "audio_rtf", "audio_duration".3. Fix script name in qwen3-omni benchmark README
File:
benchmarks/qwen3-omni/README.mdREADME referenced non-existent
extract_prompts.py. The actual script isextract_tts_prompts.py.Changed
python extract_prompts.py→python extract_tts_prompts.py.4. Lazy-import
imageioin test conftestFile:
tests/conftest.pyTop-level
import imageio.v3causedModuleNotFoundErrorfor any test run in environments withoutimageio, blocking unrelated tests (e.g., benchmark unit tests).Moved
imageioimports into the function bodies that actually need them (assert_video_validandgenerate_synthetic_video).Test Plan
Test Result
Essential Elements of an Effective PR Description Checklist
supported_models.mdandexamplesfor a new model. Please runmkdocs serveto sync the documentation editions to./docs.BEFORE SUBMITTING, PLEASE READ https://github.com/vllm-project/vllm-omni/blob/main/CONTRIBUTING.md (anything written below this line will be removed by GitHub Actions)