fix(benchmark): scrape native SGLang sidecar metrics - #367
Open
connorcarpenter15 wants to merge 3 commits into
Open
fix(benchmark): scrape native SGLang sidecar metrics#367connorcarpenter15 wants to merge 3 commits into
connorcarpenter15 wants to merge 3 commits into
Conversation
Signed-off-by: Connor Carpenter <[email protected]>
connorcarpenter15
requested review from
alec-flowers,
csahithi,
ishandhanani and
nlevin-ui
as code owners
August 29, 2026 22:46
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #367 +/- ##
=======================================
Coverage ? 72.48%
=======================================
Files ? 99
Lines ? 13572
Branches ? 0
=======================================
Hits ? 9838
Misses ? 3734
Partials ? 0 ☔ View full report in Codecov by Harness. 🚀 New features to boost your workflow:
|
Signed-off-by: Connor Carpenter <[email protected]>
Signed-off-by: Connor Carpenter <[email protected]>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Why
Native
sglang.launch_serverexposessglang:engine metrics on its HTTP port, while the Dynamo system port remains the routing endpoint. Advertising the system port to AIPerf caused otherwise successful sidecar benchmarks to fail validators that require SGLang metrics.Testing
uv run pytest tests/test_benchmarks.py::TestCustomBenchmarkRunner -q— 13 passed.uv run ruff check src/srtctl/cli/mixins/benchmark_stage.py— passed.sglang:prefix, and completed 1,106 measured requests with zero errors.