Repository navigation
fix(kserve): a GPU pool at scale-to-zero can be served — the fit check answers without a node and load proceeds - #91
Merged
Conversation
…ers without a node and load proceeds Fixes #90.
Published Helm chart
|
| Chart | model-manager |
| Version | 0.23.3-dev.kserve-poo--e-from-zero.2026-09-16.14-12-23.ha3972ae |
| OCI reference | oci://gsoci.azurecr.io/charts/giantswarm/model-manager:0.23.3-dev.kserve-poo--e-from-zero.2026-09-16.14-12-23.ha3972ae |
| Digest | sha256:6ad72a0f81f0f9860f1dc94bc0f1c4b90250c09650ebab12303874f299025c67 |
| Registry | public — gsoci.azurecr.io |
| Git catalog | giantswarm-test-catalog (index) |
Pull this chart
helm pull oci://gsoci.azurecr.io/charts/giantswarm/model-manager --version 0.23.3-dev.kserve-poo--e-from-zero.2026-09-16.14-12-23.ha3972aePosted by architect-orb · build 1230 · commit a3972ae · updated in place on every push
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
On gazelle the GPU pool
gpu-l4(cluster-manager, Karpenter, scale-to-zero) had no node, and model-manager refused to serve the first model on it (#90, seen in giantswarm/giantswarm#37714):fitCheckneeds a node matching the pool selector; with none,Fitsis false andLoad/PullreturnErrUnfit— but the pending predictor is exactly what makes the autoscaler launch the node. The pool could only be used once something else had scaled it up.Solution
When the discovery's
spec.gpuPool.nodeSelectornames a pool no node belongs to yet, and no explicit node was asked for, the fit check answersfits: truewith no node,budgetSource: pool-scale-from-zeroand a reason that says the pool scales from zero and the fit against its accelerator is unverified.LoadandPullproceed without a node pin: the predictor / download Job carry the pool's toleration and selector (scheduling.go), go Pending, and Karpenter brings the node. Unchanged: an explicit node outside the pool, a pool whose nodes exist but do not fit, and no pool selector at all (no accelerator node).TestFitCheckPoolScalesFromZero: pool selector set, no pool node → fits without a node; explicit node → refused;Loadcreates the serving object without a node pin; once a pool node exists the fit is against that node again. CHANGELOG.Verification
go test ./... -count=1: every package ok (kserve 2.5 s).golangci-lint run: 0 issues.check_fitanswer above with the pool at 0 nodes and the discovery ConfigMap'sgpuPool.nodeSelectorin effect.Plan bumblebee-plans#46 (D5/D10), epic giantswarm/giantswarm#37639.
Fixes #90.