-
Notifications
You must be signed in to change notification settings - Fork 935
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
[Bug] vllm-sr dashboard --target k8s prints a ClusterIP that cannot be opened
acceptedAccepted by the accountable Workgroup or Maintainer; not necessarily scheduled.Accepted by the accountable Workgroup or Maintainer; not necessarily scheduled.wg/developer-experience-ecosystemOwned by the Developer Experience and Ecosystem Workgroup.Owned by the Developer Experience and Ecosystem Workgroup.Status: Open.#3753 In vllm-project/semantic-router;[Feature] Expose dashboard (port 8700) in Kubernetes deployments
acceptedAccepted by the accountable Workgroup or Maintainer; not necessarily scheduled.Accepted by the accountable Workgroup or Maintainer; not necessarily scheduled.enhancementNew feature or requestNew feature or requestin-progressActively owned and under implementation.Actively owned and under implementation.wg/enterprise-environmentOwned by the Enterprise and Environment Workgroup.Owned by the Enterprise and Environment Workgroup.Status: Open.#3751 In vllm-project/semantic-router;[Enhancement]: Improve the field position or orientation while checking the Model Live Status
acceptedAccepted by the accountable Workgroup or Maintainer; not necessarily scheduled.Accepted by the accountable Workgroup or Maintainer; not necessarily scheduled.enhancementNew feature or requestNew feature or requestgood first issueGood for newcomersGood for newcomershelp wantedExtra attention is neededExtra attention is neededready-for-devAccepted, bounded, testable, and ready for an implementation owner.Accepted, bounded, testable, and ready for an implementation owner.wg/developer-experience-ecosystemOwned by the Developer Experience and Ecosystem Workgroup.Owned by the Developer Experience and Ecosystem Workgroup.Status: Open.#3742 In vllm-project/semantic-router;[Feature] Bound the key dimension in chunked_sdpa with an online softmax
acceptedAccepted by the accountable Workgroup or Maintainer; not necessarily scheduled.Accepted by the accountable Workgroup or Maintainer; not necessarily scheduled.enhancementNew feature or requestNew feature or requestwg/router-models-inference-runtimeOwned by the Router Models and Inference Runtime Workgroup.Owned by the Router Models and Inference Runtime Workgroup.Status: Open.#3737 In vllm-project/semantic-router;[Bug] Qwen3 and Gemma3 embedding attention run in f64
acceptedAccepted by the accountable Workgroup or Maintainer; not necessarily scheduled.Accepted by the accountable Workgroup or Maintainer; not necessarily scheduled.bugSomething isn't workingSomething isn't workingwg/router-models-inference-runtimeOwned by the Router Models and Inference Runtime Workgroup.Owned by the Router Models and Inference Runtime Workgroup.Status: Open.#3736 In vllm-project/semantic-router;[Feature] Report routing split, cost, and routing time consistently in bench
enhancementNew feature or requestNew feature or requestneeds-acceptanceAwaiting explicit Maintainer or Workgroup acceptance before implementation.Awaiting explicit Maintainer or Workgroup acceptance before implementation.wg/evaluation-qualityOwned by the Evaluation and Quality Workgroup.Owned by the Evaluation and Quality Workgroup.Status: Open.#3727 In vllm-project/semantic-router;[Feature] Add per-backend circuit breaker for remote classifiers
acceptedAccepted by the accountable Workgroup or Maintainer; not necessarily scheduled.Accepted by the accountable Workgroup or Maintainer; not necessarily scheduled.enhancementNew feature or requestNew feature or requestgood first issueGood for newcomersGood for newcomershelp wantedExtra attention is neededExtra attention is neededready-for-devAccepted, bounded, testable, and ready for an implementation owner.Accepted, bounded, testable, and ready for an implementation owner.wg/evaluation-qualityOwned by the Evaluation and Quality Workgroup.Owned by the Evaluation and Quality Workgroup.Status: Open.#3726 In vllm-project/semantic-router;[Bug] Playground feedback should record for all signed-in users, appear on Insights, and not let shared read accounts change routing
acceptedAccepted by the accountable Workgroup or Maintainer; not necessarily scheduled.Accepted by the accountable Workgroup or Maintainer; not necessarily scheduled.bugSomething isn't workingSomething isn't workinggood first issueGood for newcomersGood for newcomershelp wantedExtra attention is neededExtra attention is neededready-for-devAccepted, bounded, testable, and ready for an implementation owner.Accepted, bounded, testable, and ready for an implementation owner.wg/developer-experience-ecosystemOwned by the Developer Experience and Ecosystem Workgroup.Owned by the Developer Experience and Ecosystem Workgroup.Status: Open.#3725 In vllm-project/semantic-router;[Bug] plugin-request-mutations cannot reliably distinguish header overwrite from append
acceptedAccepted by the accountable Workgroup or Maintainer; not necessarily scheduled.Accepted by the accountable Workgroup or Maintainer; not necessarily scheduled.bugSomething isn't workingSomething isn't workingwg/evaluation-qualityOwned by the Evaluation and Quality Workgroup.Owned by the Evaluation and Quality Workgroup.Status: Open.#3718 In vllm-project/semantic-router;[Bug] Conversation signal reports a cumulative extraction latency for every rule after the first
acceptedAccepted by the accountable Workgroup or Maintainer; not necessarily scheduled.Accepted by the accountable Workgroup or Maintainer; not necessarily scheduled.bugSomething isn't workingSomething isn't workingwg/router-models-inference-runtimeOwned by the Router Models and Inference Runtime Workgroup.Owned by the Router Models and Inference Runtime Workgroup.Status: Open.#3715 In vllm-project/semantic-router;[Bug] Signal match and extraction metrics skip recipe scoping at five call sites
acceptedAccepted by the accountable Workgroup or Maintainer; not necessarily scheduled.Accepted by the accountable Workgroup or Maintainer; not necessarily scheduled.bugSomething isn't workingSomething isn't workingwg/router-models-inference-runtimeOwned by the Router Models and Inference Runtime Workgroup.Owned by the Router Models and Inference Runtime Workgroup.Status: Open.#3714 In vllm-project/semantic-router;[Bug] Keyword rules never match keywords that start or end with a symbol or a non-ASCII letter
acceptedAccepted by the accountable Workgroup or Maintainer; not necessarily scheduled.Accepted by the accountable Workgroup or Maintainer; not necessarily scheduled.bugSomething isn't workingSomething isn't workingin-progressActively owned and under implementation.Actively owned and under implementation.wg/mom-routingOwned by the MoM and Routing Workgroup.Owned by the MoM and Routing Workgroup.Status: Open.#3710 In vllm-project/semantic-router;