Skip to content

ci(benchmark): add automated benchmark CI workflow#130

Draft
yehuditkerido wants to merge 1 commit into
llm-d:mainfrom
yehuditkerido:add_benchmark_job
Draft

ci(benchmark): add automated benchmark CI workflow#130
yehuditkerido wants to merge 1 commit into
llm-d:mainfrom
yehuditkerido:add_benchmark_job

Conversation

@yehuditkerido

Copy link
Copy Markdown
Contributor

What type of PR is this?
/kind feature
/kind ci

What this PR does / why we need it:
Add automated benchmark CI workflow that runs on every PR, compares performance against main branch, posts results as PR comment, and adds perf-regression label if allocations increase >20%.

Which issue(s) this PR fixes:
Fixes #114

Release note:

NONE

Signed-off-by: Yehudit Kerido <ykerido@redhat.com>
@github-actions github-actions Bot added size/L Denotes a PR that changes 100-499 lines, ignoring generated files. kind/feature Categorizes issue or PR as related to a new feature. labels May 25, 2026
@yehuditkerido yehuditkerido marked this pull request as draft June 14, 2026 05:59
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

kind/feature Categorizes issue or PR as related to a new feature. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

perf: ModelSelectorProfile allocates memory per-model on every request

1 participant