llmd router metrics collector plugin.#215
Open
Mohammad-nassar10 wants to merge 5 commits into
Open
Conversation
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Mohammad-nassar10
marked this pull request as draft
July 6, 2026 14:18
github-actions
Bot
added
the
size/L
Contributor
|
can you rename the plugin to reflect that it is a llm-d router metrics collector? |
ronenkat
reviewed
Jul 7, 2026
ronenkat
left a comment
ronenkat
left a comment
Contributor
There was a problem hiding this comment.
@Mohammad-nassar10 please create an issue describing the motivation for the collector (i.e., black-box vs. white-box understanding of the inference pool)
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
github-actions
Bot
added
the
kind/feature
Signed-off-by: Mohammad-nassar10 <79787844+Mohammad-nassar10@users.noreply.github.com>
Signed-off-by: Mohammad <mohammad.nassar@ibm.com>
Mohammad-nassar10
marked this pull request as ready for review
July 12, 2026 16:28
github-actions
Bot
added
kind/feature
Mohammad-nassar10
changed the title
github-actions
Bot
added
kind/feature
Signed-off-by: Mohammad-nassar10 <79787844+Mohammad-nassar10@users.noreply.github.com>
ronenkat
reviewed
Jul 15, 2026
| parameters: | ||
| interval: "30s" | ||
| timeout: "5s" | ||
| utilizationMetric: "vllm:kv_cache_usage_perc" |
Contributor
There was a problem hiding this comment.
shouldn't the default be something like llm_d_epp_average_kv_cache_utilization ?
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What type of PR is this?
/kind feature
What this PR does / why we need it:
Adds the
llmd-router-metrics-collectordatalayer plugin, which polls each model's pool-aggregated Prometheus endpoint on a configurable interval and writes adatalayer.RouterMetricsattribute per model. This gives downstream scorer plugins white-box access to KV-cache pressure, queue depth, and running request counts.Which issue(s) this PR fixes:
Fixes #235.
Release note (write
NONEif no user-facing change):