Skip to content

Adds an inflight-requests scorer#94

Open
Mohammad-nassar10 wants to merge 59 commits into
llm-d:mainfrom
Mohammad-nassar10:run-req-scorer
Open

Adds an inflight-requests scorer#94
Mohammad-nassar10 wants to merge 59 commits into
llm-d:mainfrom
Mohammad-nassar10:run-req-scorer

Conversation

@Mohammad-nassar10
Copy link
Copy Markdown
Contributor

@Mohammad-nassar10 Mohammad-nassar10 commented May 14, 2026

What does this PR do?

Add a simple running-requests scorer to score models based on their current in-flight request count, ranking the least loaded model highest by assigning a normalized score in [0.0, 1.0]. The most loaded model receives a score of 0.0, and the least loaded receives a score of 1.0.

Note: This PR is stacked on #75. Because both PRs target main,
merge #75 first.

Why is this change needed?

How was this tested?

  • Unit tests added/updated
  • Integration/e2e tests added/updated
  • Manual testing performed

Checklist

  • Commits are signed off (git commit -s) per DCO
  • Code follows project contributing guidelines
  • Tests pass locally (make test)
  • Linters pass (make lint)
  • Documentation updated (if applicable)

Related Issues

Fixes issue #93.

Mohammad-nassar10 and others added 20 commits May 10, 2026 23:43
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad-nassar10 <79787844+Mohammad-nassar10@users.noreply.github.com>
Signed-off-by: Mohammad-nassar10 <79787844+Mohammad-nassar10@users.noreply.github.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
@github-actions github-actions Bot added the size/L Denotes a PR that changes 100-499 lines, ignoring generated files. label May 14, 2026
@Mohammad-nassar10 Mohammad-nassar10 changed the title Adds a simple running-requests scorer Adds a running-requests scorer May 14, 2026
Comment thread pkg/framework/modelselector/scorer/inflightrequests/plugin.go Outdated
Mohammad-nassar10 and others added 20 commits May 17, 2026 11:14
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad-nassar10 <79787844+Mohammad-nassar10@users.noreply.github.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
@Mohammad-nassar10
Copy link
Copy Markdown
Contributor Author

/cc @shmuelk

@shmuelk
Copy link
Copy Markdown
Collaborator

shmuelk commented May 19, 2026

Please add the code to register the plugin

Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
@Mohammad-nassar10
Copy link
Copy Markdown
Contributor Author

@shmuelk Added, thanks!

Mohammad-nassar10 and others added 4 commits May 20, 2026 11:56
Signed-off-by: Mohammad-nassar10 <79787844+Mohammad-nassar10@users.noreply.github.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Signed-off-by: Mohammad-nassar10 <79787844+Mohammad-nassar10@users.noreply.github.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

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.

4 participants