Add scorer based on active loras #43
Open
Conversation
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
…ill be the target for a request. Session affinity scorer added
- Rename SessionId to SessionID - Remove datastore from scoreTargets, add datastore to SessionAffinityScorer - Rename ScoredPod to PodScore
…f ScoreMng - If some specific scorer failed to score pods - just log the problem, skip it and continue to the next scorer
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
Bumps [golang.org/x/net](https://github.com/golang/net) from 0.37.0 to 0.38.0. - [Commits](golang/net@v0.37.0...v0.38.0) --- updated-dependencies: - dependency-name: golang.org/x/net dependency-version: 0.38.0 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com>
…odules/golang.org/x/net-0.38.0 Bump golang.org/x/net from 0.37.0 to 0.38.0
Add scorers support in scheduler
…ev-deployments First iteration of development deployments & environments
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
…e-builds fix: basic container image builds for linux
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Etai Lev Ran <elevran@gmail.com>
…on_yaml empty top level kustomization.yaml - make CICD happy
Patch Istio deployment to use 1Gi of mem
Setup the Istio service to be a NodePort service and not a ClusterIP service
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
…t-env Add openshift-infra dev env deployment
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
Signed-off-by: Shane Utt <shaneutt@linux.com>
feat: add kubernetes dev env
|
please rebase/resubmit with less clutter - the PR pulled in too many files from other PRs |
elevran
reviewed
Apr 27, 2025
| @@ -104,36 +105,58 @@ func (p *PodMetricsClientImpl) promToPodMetrics( | |||
|
|
|||
| // Handle LoRA metrics (only if all LoRA MetricSpecs are present) | |||
| if p.MetricMapping.LoraRequestInfo != nil { | |||
| loraMetrics, err := p.getLatestLoraMetric(metricFamilies) | |||
There was a problem hiding this comment.
nit: Please try to be more consistent in use of lora, Lora, LoRA (avoiding symbol exports of course...)
| errs = multierr.Append(errs, err) | ||
|
|
||
| if err == nil { | ||
| updated.ActiveModels = make(map[string]int) |
There was a problem hiding this comment.
q: is the int value useful or used to implement a Set using a hashtable?
If Set, consider using map[string]struct{} (see here for a complete example)
There was a problem hiding this comment.
would it be possible to put all LoRA related stuff in its own file/directory?
There was a problem hiding this comment.
Prefer a directory per filter/scorer or other organization that keeps new code from the GIE original directories whenever possible.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Given a model name (in case this is a LoRA adapter) each pod will get score based on whether the lora is currently in the running/waiting loras list.