volcano-sh

Issues somebody may already be working on are listed last. List everything by date

• tokenizer: waitReady allocates a new time.After timer on every poll iteration (timer leak)

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 2/5 1-3 hours Newbie friendliness 58/100

  volcano-sh/kthena#2023 · Opened Nov 11, 2026

  Maintainers usually reply within 1 day

• router: kvcache-aware plugin aborts all scoring on any Redis pipeline error (partial failures not tolerated)

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 2/5 1-3 hours Newbie friendliness 68/100

  volcano-sh/kthena#2022 · Opened Nov 11, 2026

  Maintainers usually reply within 1 day

• router: fairness queue never rebuilds heap under high load (shouldRebuildLocked condition inverted)

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 1/5 Under an hour Newbie friendliness 70/100

  volcano-sh/kthena#2021 · Opened Nov 11, 2026

  Maintainers usually reply within 1 day

• pg-controller moves a StatefulSet's PodGroup from its namespace queue to "default" on rollout restart

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 2/5 1-3 hours Newbie friendliness 76/100

  volcano-sh/volcano#6292 · 1 comment · Opened Nov 11, 2026

  Maintainers usually reply within 1 day

• CNCF Graduation Application Tracking

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 4/5 3-5 days Newbie friendliness 35/100

  volcano-sh/community#173 · 1 comment · Opened Nov 10, 2026

• Request for Feedback on Production Upgrade Needs

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  question

  Difficulty 1/5 Under an hour Newbie friendliness 25/100

  volcano-sh/agentcube#504 · 1 comment · Opened Nov 5, 2026

  Maintainers usually reply within 1 day

• Proposal: heat-aware plugin for batch and AI training jobs

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 5/5 Over a week Newbie friendliness 15/100

  volcano-sh/volcano#6226 · Opened Nov 3, 2026

  Maintainers usually reply within 1 day

• Expose resolved members in HyperNode status

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/feature

  Difficulty 5/5 Over a week Newbie friendliness 35/100

  volcano-sh/volcano#6192 · 2 comments · Opened Oct 29, 2026

  Maintainers usually reply within 1 day

• Release v1.17.0 Roadmap

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  milestone

  Difficulty 5/5 Over a week Newbie friendliness 25/100

  volcano-sh/volcano#6166 · 2 comments · Opened Oct 27, 2026

  Maintainers usually reply within 1 day

• Any idea about networkTopologyAware strategy when NVIDIA-GB300-NVL72 in k8s cluster

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/question

  Difficulty 5/5 Over a week Newbie friendliness 35/100

  volcano-sh/volcano#6135 · 1 comment · Opened Oct 21, 2026

  Maintainers usually reply within 1 day

• [Umbrella] Move shared Queue hierarchy and accounting out of plugins

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/feature

  Difficulty 5/5 Over a week Newbie friendliness 25/100

  volcano-sh/volcano#6128 · 2 comments · Opened Oct 20, 2026

  Maintainers usually reply within 1 day

• fairshare: a failed load of persisted state is never retried, and the next flush overwrites the usage history

  May be free again @btxu-db claimed this 34 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  volcano-sh/volcano#6070 · 1 comment · 1 assignee · Opened Oct 9, 2026

  Maintainers usually reply within 1 day

• [Feature] Integrate HyperNode with kube-scheduler and coscheduling plugins

  May be free again @JesseStutler claimed this 45 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  area/scheduling kind/feature

  volcano-sh/volcano#6028 · 1 comment · 1 assignee · Opened Sep 29, 2026

  Maintainers usually reply within 1 day

• bug: ModelServing maxSurge rollouts finish with missing ordinal 0 and retain a temporary high ordinal

  May be free again @VanderChen claimed this 47 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  volcano-sh/kthena#1833 · 1 comment · 1 assignee · Opened Sep 27, 2026

  Maintainers usually reply within 1 day

• [release-1.15] feat(helm): allow configuring admission root queue protection via values.yaml

  Possibly taken @JesseStutler claimed this 1 day ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  volcano-sh/volcano#6298 · 1 reaction · 2 assignees · Opened Nov 12, 2026

  Maintainers usually reply within 1 day

• Unify daily release image builds for Docker Hub and GHCR to avoid job timeouts

  Possibly taken @JesseStutler claimed this 1 day ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  area/ci

  volcano-sh/volcano#6295 · 1 reaction · 2 assignees · Opened Nov 12, 2026

  Maintainers usually reply within 1 day

• gangpreempt can evict PDB-protected Pods even when unprotected alternatives are available

  Possibly taken @mohitvinchoo claimed this today. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  Difficulty 4/5 3-5 days Newbie friendliness 45/100

  volcano-sh/volcano#6294 · 1 comment · Opened Nov 11, 2026

  Maintainers usually reply within 1 day

• kvcache-aware (Redis mode): evicting one block removes the pod from a block hash it still caches

  Possibly taken @Anand-240 claimed this 2 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  volcano-sh/kthena#2010 · 1 comment · 1 assignee · Opened Nov 10, 2026

  Maintainers usually reply within 1 day

• router: changing a Gateway listener's hostname can leave its port dead (bind: address already in use)

  Possibly taken @shubhamkumar9199 claimed this 2 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  volcano-sh/kthena#2008 · 1 comment · 1 assignee · Opened Nov 10, 2026

  Maintainers usually reply within 1 day

• [Bug] Updating ReplicaSet annotations does not propagate to existing Volcano-managed PodGroups

  Possibly taken @AyushSrivastava1818 claimed this 3 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  volcano-sh/volcano#6279 · 1 comment · 1 assignee · Opened Nov 10, 2026

  Maintainers usually reply within 1 day

• [release-1.15] scheduler: restore an unevicted victim in the predicates node info

  Possibly taken @JesseStutler claimed this 3 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  volcano-sh/volcano#6268 · 1 reaction · 2 assignees · Opened Nov 10, 2026

  Maintainers usually reply within 1 day

• router: Start returns before graceful shutdown finishes, so in-flight requests are cut off on SIGTERM

  Possibly taken @Paramveersingh-S claimed this 3 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  Difficulty 2/5 1-3 hours Newbie friendliness 52/100

  volcano-sh/agentcube#508 · Opened Nov 8, 2026

  Maintainers usually reply within 1 day

• cli: DeepSeek-R1-Distill-Qwen-32B template renders invalid YAML, so kthena create manifest fails

  Possibly taken @Daksha1611 claimed this 5 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 2/5 1-3 hours Newbie friendliness 25/100

  volcano-sh/kthena#1981 · Opened Nov 8, 2026

  Maintainers usually reply within 1 day

• Tokenizer service abandons a model once its lifetime restart count reaches RENDERER_MAX_RESTARTS

  Possibly taken @iamtanishqjain claimed this 5 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 1/5 Under an hour Newbie friendliness 25/100

  volcano-sh/kthena#1979 · Opened Nov 7, 2026

  Maintainers usually reply within 1 day

• runtime: /v1/download_model and /v1/load_lora_adapter return 500 for a non-empty config object

  Possibly taken @Daksha1611 claimed this 6 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 2/5 1-3 hours Newbie friendliness 79/100

  volcano-sh/kthena#1976 · Opened Nov 6, 2026

  Maintainers usually reply within 1 day

• [Feature Request] Support Redis authentication for session-sticky storage

  Possibly taken @Veditha08 claimed this 5 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/enhancement

  Difficulty 4/5 3-5 days Newbie friendliness 55/100

  volcano-sh/kthena#1974 · 1 comment · Opened Nov 6, 2026

  Maintainers usually reply within 1 day

• Avoid scanning all Jobs in a namespace during CronJob reconciliation

  Possibly taken @Samar-Singla claimed this 6 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/feature

  Difficulty 4/5 3-5 days Newbie friendliness 56/100

  volcano-sh/volcano#6245 · Opened Nov 6, 2026

  Maintainers usually reply within 1 day

• gangpreempt does not preempt within a queue whose nodegroup resource limit is used up

  Possibly taken @fqix claimed this 4 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  Difficulty 4/5 3-5 days Newbie friendliness 49/100

  volcano-sh/volcano#6244 · 3 comments · 1 assignee · Opened Nov 6, 2026

  Maintainers usually reply within 1 day

• docs: audit scheduler and job plugins and add documentation index

  Possibly taken @SoumaCloud claimed this 8 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  volcano-sh/website#600 · 1 comment · 1 assignee · Opened Nov 5, 2026

  Maintainers usually reply within 1 day

• docs: add PodGroup anti-affinity examples for inference placement across HyperNodes

  Possibly taken @SoumaCloud claimed this 8 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  volcano-sh/website#599 · 1 comment · 1 assignee · Opened Nov 5, 2026

  Maintainers usually reply within 1 day

• ModelServing: a late Pod delete event can delete its healthy replacement

  Possibly taken @aeron-gh claimed this 9 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  volcano-sh/kthena#1957 · 2 comments · 1 assignee · Opened Nov 3, 2026

  Maintainers usually reply within 1 day

• docs: refresh homepage ecosystem cards with KubeRay, Grove, and LeaderWorkerSet

  Possibly taken @lmilbaum claimed this 5 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 3/5 1-2 days Newbie friendliness 65/100

  volcano-sh/website#597 · Opened Nov 3, 2026

  Maintainers usually reply within 1 day

• ModelServing: a persistently failing Role or ServingGroup is recreated endlessly with no backoff

  Possibly taken @kube-gopher claimed this 10 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/enhancement

  volcano-sh/kthena#1951 · 3 comments · 1 assignee · Opened Nov 3, 2026

  Maintainers usually reply within 1 day

• docs: invalid JSON syntax with trailing commas in colocation overview configuration snippets

  Possibly taken @Hpsingh26 claimed this 10 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  volcano-sh/volcano#6231 · 1 comment · 1 assignee · Opened Nov 3, 2026

  Maintainers usually reply within 1 day

• [Feature] Support multiple worker tasks in the MPI job plugin for heterogeneous MPI jobs

  Possibly taken @kingeasternsun claimed this 10 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 3/5 1-2 days Newbie friendliness 15/100

  volcano-sh/volcano#6229 · 1 comment · Opened Nov 3, 2026

  Maintainers usually reply within 1 day

• Add error-path tests for handleDeleteSandbox to verify Kubernetes and store consistency

  Possibly taken @SoumaCloud claimed this 10 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  volcano-sh/agentcube#500 · 6 comments · 1 assignee · Opened Nov 2, 2026

  Maintainers usually reply within 1 day

• PicoD subprocess execution does not respect incoming HTTP request cancellation

  Possibly taken @SoumaCloud claimed this 10 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  volcano-sh/agentcube#499 · 7 comments · 1 assignee · Opened Nov 2, 2026

  Maintainers usually reply within 1 day

• Autoscaler reconciliation goroutine does not stop when the controller context is cancelled

  Possibly taken @SoumaCloud claimed this 10 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  volcano-sh/kthena#1948 · 1 comment · 1 assignee · Opened Nov 2, 2026

  Maintainers usually reply within 1 day

• deviceshare: Align binpack and spread score timing between NVIDIA vGPU and Ascend HAMi

  Possibly taken @SiuMai99 claimed this 10 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug priority/awaiting-more-evidence

  volcano-sh/volcano#6223 · 4 comments · 1 assignee · Opened Nov 2, 2026

  Maintainers usually reply within 1 day

• [Umbrella] Refresh website architecture, key features, plugins, and ecosystem docs

  Possibly taken @JesseStutler claimed this 11 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  volcano-sh/website#595 · 12 comments · 1 assignee · Opened Nov 2, 2026

  Maintainers usually reply within 1 day

• PD scheduler fails to find valid Prefill-Decode pairs beyond top five Decode candidates

  Possibly taken @chandan009s claimed this 12 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  volcano-sh/kthena#1941 · 1 comment · 1 assignee · Opened Nov 1, 2026

  Maintainers usually reply within 1 day

• router: failed response headers contaminate a healthy backend retry

  Possibly taken @saylee21 claimed this 7 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 3/5 1-2 days Newbie friendliness 45/100

  volcano-sh/kthena#1936 · 1 comment · Opened Oct 31, 2026

  Maintainers usually reply within 1 day

• webhook: scheduling gate is not injected when admission config fails to load

  Possibly taken @Ironankit525 claimed this 12 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  volcano-sh/volcano#6211 · 1 comment · 1 assignee · Opened Oct 31, 2026

  Maintainers usually reply within 1 day

• cronjob: names of 46–52 chars pass admission, but every Job they create fails pod-name validation

  Possibly taken @CapThunder19 claimed this 13 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  volcano-sh/volcano#6206 · 3 comments · 1 assignee · Opened Oct 30, 2026

  Maintainers usually reply within 1 day

• Gang unschedulable counts differ across Pod, PodGroup condition, and Event

  Possibly taken @vishalmore90 claimed this 14 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  volcano-sh/volcano#6200 · 3 comments · 1 reaction · 1 assignee · Opened Oct 29, 2026

  Maintainers usually reply within 1 day

• Prometheus metrics collection leaves idle connections open and creates a new transport for each node

  Possibly taken @Samar-Singla claimed this 14 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  Difficulty 3/5 1-2 days Newbie friendliness 35/100

  volcano-sh/volcano#6198 · Opened Oct 29, 2026

  Maintainers usually reply within 1 day

• cdp: cooldown-time counts from bind time, so pods with slow start-up can be preempted right after they start running

  Possibly taken @GuTS805 claimed this 14 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  volcano-sh/volcano#6197 · 1 comment · 1 assignee · Opened Oct 29, 2026

  Maintainers usually reply within 1 day

• Rolled-back Pipeline candidates cause repeated Pod status updates

  Possibly taken @wangyang0616 claimed this 14 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug priority/high

  volcano-sh/volcano#6196 · 6 comments · 2 assignees · Opened Oct 29, 2026

  Maintainers usually reply within 1 day

• router: data races found by go test -race

  Possibly taken @Abhayanthk claimed this 15 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  kind/bug

  volcano-sh/kthena#1920 · 1 comment · 1 assignee · Opened Oct 29, 2026

  Maintainers usually reply within 1 day

• klog.Info and klog.Error misuse key/value arguments, producing concatenated log messages

  Possibly taken @Karman580 claimed this 15 days ago. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 2/5 1-3 hours Newbie friendliness 35/100

  volcano-sh/volcano#6194 · Opened Oct 29, 2026

  Maintainers usually reply within 1 day