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

Add server metrics promql scraping #804

Merged
merged 3 commits into from
Sep 12, 2024
Merged

Add server metrics promql scraping #804

merged 3 commits into from
Sep 12, 2024

Conversation

annapendleton
Copy link
Collaborator

@annapendleton annapendleton commented Sep 11, 2024 •
edited
Loading

Add initial implementation for scraping server side metrics for analysis.

Initial implementation includes support for vLLM and Jetstream.

Validated end to end, example output at end of output file:

Metric Name: vllm:gpu_cache_usage_perc
Mean: 0.6996527777777777
Median: 0.8744212962962963
Min: 0.05439814814814814
Max: 0.9953703703703703
P90: 0.9936342592592593
P99: 0.9951967592592592
Metric Name: vllm:num_requests_waiting
Mean: 25.75
Median: 2.5
Min: 0
Max: 98
P90: 70.10000000000002
P99: 95.20999999999998

@raywainman
Copy link
Collaborator

/lgtm

@annapendleton annapendleton merged commit 939b05a into GoogleCloudPlatform:main Sep 12, 2024
7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@achandrasekar achandrasekar achandrasekar approved these changes

@Bslabe123 Bslabe123 Awaiting requested review from Bslabe123

@ahg-g ahg-g Awaiting requested review from ahg-g ahg-g is a code owner

@raywainman raywainman Awaiting requested review from raywainman

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

Successfully merging this pull request may close these issues.
3 participants
@annapendleton @raywainman @achandrasekar