Issues
- 0
ClusterRole permissions are too broadly scoped?
#3724 opened by jssnirmal - 3
Support text embedding task in huggingface server
#3572 opened by kevinmingtarja - 0
- 3
Autoscaling with multiple metrics does not work
#3638 opened by shazinahmed - 3
Release 0.13 Tracking
#3648 opened by yuzisun - 1
- 0
Make MAX_GRPC_MESSAGE_LENGTH Configurable for Image Input Size Flexibility
#3717 opened by anencore94 - 7
- 12
Cannot re-initialize CUDA in forked subprocess. To use CUDA with multiprocessing, you must use the 'spawn' start method
#3662 opened by serdarildercaglar - 0
Inference gRPC/Rest client to support FP16
#3643 opened by yuzisun - 12
Unable to run InferenceService on a local cluster
#3689 opened by yurkoff-mv - 1
Is there a way to supply a token to the hugging face inference server run time?
#3693 opened by empath-nirvana - 0
- 3
InferenceService Model Transition in Pending/InProgress forever while inference service is operational
#3686 opened by CanmingCobble - 1
Make label and annotation propagation configurable
#3710 opened by cmaddalozzo - 0
Update to AWS Go SDK v2
#3709 opened by mattjohnsonpint - 2
Support ollama server
#3647 opened by skonto - 0
- 8
Discuss the future of models-webapp
#3625 opened by rimolive - 2
Merge responses from InferenceGraph Sequence node steps
#3639 opened by asd981256 - 12
Allow PVC Model Mount in ReadWrite Mode
#3687 opened by supertetelman - 0
Download files from Azure storage under virtual directory for Multi-model serving
#3691 opened by leduckhc - 1
Update image container image but the associated predictor pod image is not change
#3683 opened by kwjerrychan - 8
- 0
Scale pods based on a cron schedule
#3597 opened by vukor - 1
Add vLLM backend e2e test
#3644 opened by yuzisun - 2
Allow remote code execution on huggingfaceserver
#3580 opened by isaranto - 0
Allow re-running of failed workflows
#3631 opened by andyi2it - 1
Support suspending InferenceService
#3675 opened by tenzen-y - 0
protocolVersion used by the predictor
#3674 opened by Csehpi - 5
- 3
- 1
Update deprecated generate-groups.sh to kube_codegen
#3667 opened by spolti - 2
- 0
Add a provision in KServe repo to allow cherry pick of PRs to release branches
#3656 opened by andyi2it - 3
Kserve deployment certificate issue - tls: failed to verify certificate: x509: certificate signed by unknown authority\nError from server (InternalError)
#3649 opened by Subhankar-Adak - 0
- 3
- 0
- 0
Record ownerReferences on managed ingress
#3636 opened by backjo - 0
Add metadata to logger system
#3634 opened by gcemaj - 1
- 2
Custom ClusterServingRuntime not being selected based on modelFormat Name/Version without runtime specification
#3632 opened by supertetelman - 3
Parallel Model Inference with Ray Serving not working due to deprecated API
#3595 opened by ajstewart - 0
Update exclusion list for go lint and Fix Go lint errors
#3608 opened by andyi2it - 0
Fix new Golang security vulnerability - CVE-2024-24786
#3602 opened by andyi2it - 1
Old Revisions of Inference Service not Scaled Down
#3591 opened by ksgnextuple - 0
Add parameter in ModelMetadataResponse in v2 (aka open inference) protocol
#3574 opened by harshita-meena - 2
Go Coverage action is failing in CI
#3563 opened by sivanantha321 - 0
Use black to auto-format Python code
#3567 opened by cmaddalozzo