chore(deps): update kserve-crd docker tag to v0.18.0

[renovate]

ℹ️ Note

This PR body was truncated due to platform limits.

This PR contains the following updates:

Package	Update	Change
kserve-crd (source)	minor	v0.16.0 → v0.18.0

---

Release Notes

kserve/kserve (kserve-crd)

v0.18.0

Compare Source

What's Changed

• build(make): add optional overrides include to Makefile by @​bartoszmajsak in #​5164
• fix: skip _folder to package helm chart by @​Jooho in #​5186
• refactor(e2e/llmisvc): flexible endpoint testing by @​bartoszmajsak in #​5093
• refactor: change kserve chart name to kserve-resources by @​Jooho in #​5190
• feat(release): add draft release automation and improve release process by @​Jooho in #​5191
• feat: 5060 CSV and Parquet marshallers by @​cjohannsen-cloudera in #​5115
• feat(ci): conditionally trigger helm or kustomize e2e tests based on … by @​Jooho in #​5193
• fix(llmisvc): resolve LWS leader address for ZMQ and increase /dev/shm by @​bartoszmajsak in #​5155
• fix(utils): prevent overwriting existing SecurityContext when configu… by @​fyuan1316 in #​5167
• chore: add MAINTAINERS.md for LFX Insights by @​terrytangyuan in #​5195
• feat(logger): log occurrence and record time in CloudEvents by @​samuelkim7 in #​5139
• fix(llmisvc): handle missing LWS CRD gracefully by @​bartoszmajsak in #​5201
• feat: include GIE CRDs as part of Kserve bundle by @​pierDipi in #​5214
• fix: add helm chart version to kserve-runtime-configs by @​Jooho in #​5209
• modelcache: add Namespace Scoped ModelCache by @​VedantMahabaleshwarkar in #​4887
• release: prepare release v0.17.0-rc1 by @​Jooho in #​5222
• fix(llmisvc): add validations for unsupported scaling configurations by @​vivekk16 in #​5212
• fix(make): increase test timeout from 20m to 30m by @​bartoszmajsak in #​5165
• fix: improve cherry-pick workflow with validation and PR fetch by @​Jooho in #​5233
• chore: bump kustomize from v5.5.0 to v5.8.0 by @​bartoszmajsak in #​5218
• feat(llmisvc): add build hooks for distribution-specific logic by @​bartoszmajsak in #​5217
• test(llmisvc): unit tests for versioned config resolution by @​bartoszmajsak in #​5182
• fix: resolve go test -cover failure by @​bartoszmajsak in #​5178
• fix(build): fall back to existing version when URL verification fails by @​bartoszmajsak in #​5180
• feat: allow configuring GatewayClass for llmisvc e2e tests by @​pierDipi in #​5238
• feat: upgrade llm-d to 0.6 by @​pierDipi in #​5121
• fix(llmisvc): add default for MinReplicas & make MaxReplicas required int32 by @​vivekk16 in #​5237
• feat(llmisvc): add --disable-uvicorn-access-log to vllm configs by @​pierDipi in #​5154
• feat: merge target branch in each GH action job by @​pierDipi in #​5232
• feat(llmisvc): implement autoscaling for WVA and KEDA/HPA integration by @​vivekk16 in #​5194
• feat: add storage migration for LLMinferenceService APIs by @​pierDipi in #​5149
• fix(llmisvc): add missing os.Exit(1) after controller setup failure by @​vivekk16 in #​5242
• fix: change wrong crd kustomization update by @​spolti in #​5234
• fix: to install specific kserve version with kustomize script by @​Jooho in #​5247
• test(llmisvc): add envtest integration tests for scaling reconciliation by @​vivekk16 in #​5246
• release: prepare release v0.17.0 by @​Jooho in #​5248
• feat(llmisvc): evaluate both InferencePool readiness by @​bartoszmajsak in #​5202
• fix(ci): configure git identity for merge commits in CI workflows by @​pierDipi in #​5251
• feat(llmisvc): update LLMInferenceServiceConfig and add TLS flag by @​pierDipi in #​5249
• chore: migrate Python formatter from black to ruff format by @​jlost in #​5000
• fix(ci): add readiness to seaweedfs deployment by @​pierDipi in #​5267
• feat: replace vllm-cpu image with upstream built image by @​pierDipi in #​5264
• fix(e2e): retry predict on transient gateway errors by @​pierDipi in #​5266
• feat: enable scheduler TLS cert reload by @​pierDipi in #​5260
• feat: adding version overrides helm chart dependencies by @​andresllh in #​5268
• fix(ci): restrict workflow re-run to repo collaborators by @​bartoszmajsak in #​5280
• fix: prevent double-build when pushing llmisvc-controller image by @​israel-hdez in #​5207
• chore(ci): align action versions across workflows by @​bartoszmajsak in #​5277
• fix(ci): correct self-referencing path in llmisvc docker workflow by @​bartoszmajsak in #​5275
• fix(ci): add missing disk space cleanup to docker push jobs by @​bartoszmajsak in #​5278
• chore: support for merge queue by @​israel-hdez in #​5253
• ci: optimize Go Dockerfiles for faster CI builds by @​bartoszmajsak in #​5273
• modelcache: run namespace-scoped download jobs in jobNamespace by @​VedantMahabaleshwarkar in #​5262
• chore(ci): remove redundant Go dependency download step by @​bartoszmajsak in #​5279
• ci: improve GHA runner infra (disk cleanup, minikube addons) by @​bartoszmajsak in #​5281
• feat(llmisvc): add extra_headers to wait_for_model_response by @​jlost in #​5215
• feat(localmodel): add build hooks for distribution-specific logic by @​VedantMahabaleshwarkar in #​5263
• [WIP] feat: detect Gateway for auto-migration to v1 InferencePool by @​pierDipi in #​5041
• fix: include 0.17.0 installation scripts by @​Jooho in #​5256
• fix: replace MD5 with SHA-256 in e2e fixtures by @​maskarb in #​5271
• fix: "[WIP] feat: detect Gateway for auto-migration to v1 InferencePool" by @​pierDipi in #​5316
• fix(llmisvc): migrate tokenProcessorConfig and blockSize by @​pierDipi in #​5305
• ci: improvements for setup-uv and build-graph image by @​bartoszmajsak in #​5220
• build: optimize Python Dockerfile caching and build context by @​bartoszmajsak in #​5274
• chore: bump mlserver seldon image to latest 1.7.1 by @​seBasKov in #​4573
• fix(llmisvc): autoscaling config logging by @​Gregory-Pereira in #​5304
• fix(llmisvc): remove unreachable RefsInvalid early-return guards by @​bartoszmajsak in #​5288
• chore(hack): remove legacy quick install scripts by @​Jooho in #​5289
• refactor(test): migrate pod webhook suite to centralized envtest setup by @​bartoszmajsak in #​5179
• chore: fix CVE-2026-32597 PyJWT crit header validation by @​spolti in #​5283
• feat: update .gitattributes with all generated files by @​pierDipi in #​5258
• fix(deps): bump go.opentelemetry.io/otel/sdk to v1.40.0 by @​SebastienSyd in #​5199
• chore(config): clean up trailing whitespaces by @​juhyeon-cha in #​5300
• fix(llmisvc): remove cert-hash restart annotation from scheduler by @​bartoszmajsak in #​5308
• fix(llmisvc): defer storage migration until webhooks are serving by @​bartoszmajsak in #​5286
• fix(controllers): gracefully handle resource deletion by @​bartoszmajsak in #​5252
• fix(build): pin setup-envtest by @​bartoszmajsak in #​5323
• chore: pin standalone kustomize and decouple from kubectl by @​jlost in #​5322
• ci: reduce Go image build times by @​bartoszmajsak in #​5287
• refactor(llmisvc): simplify EPPServiceName guard logic by @​bartoszmajsak in #​5107
• feat(llmisvc): propagate imagePullSecrets from default SA by @​pierDipi in #​5324
• test: centralizes logger setup by @​bartoszmajsak in #​5042
• fix: merge automation by @​pierDipi in #​5328
• ci: add pinact to pin GitHub Actions to SHA by @​pierDipi in #​5320
• fix(test): ensures GinkgoRecover is used correctly by @​bartoszmajsak in #​5171
• fix(ci): pins github actions in license check by @​bartoszmajsak in #​5329
• fix(ci): 'commit not found' in go-security-scan upload-sarif by @​Jooho in #​5336
• feat(llmisvc): upgrade WVA dependency from v0.5.1 to v0.6.0-rc3 by @​vivekk16 in #​5333
• docs: add e2e guide for running GPT-OSS-20B with LLMInferenceService by @​sbekkerm in #​5150
• fix: 5337: upgrade vLLM to 0.17.1 by @​cjohannsen-cloudera in #​5338
• feat: add offset_mapping output for HuggingFace token classification by @​Yuuuuuu0319 in #​5244
• fix(llmisvc): always set status.URL with a discovered address by @​pierDipi in #​5339
• feat(ingress): add DisableHTTPRouteTimeout config flag for GKE Gateway by @​sophieliu15 in #​5313
• feat: add /v1/responses HTTPRoute for OpenAI Responses API support by @​RishabhSaini in #​5291
• chore(llmisvc): bump LLMISvc dependency versions by @​vivekk16 in #​5344
• feat: block PYTHONPATH env var in ISVC and ServingRuntime webhooks by @​Jooho in #​5340
• fix(llmisvc): upgrading to LLM-D v0.6.0 for llmisvc by @​Gregory-Pereira in #​5346
• feat(llmisvc): add platform hooks for networking and manager cfg by @​bartoszmajsak in #​5240
• feat(llmisvc): enable LWS as autoscaling target for multi-node workloads by @​vivekk16 in #​5356
• fix: hardcode Status.Address scheme to http in raw deployment by @​jlost in #​5363
• chore: remove coverage badge by @​israel-hdez in #​5298
• feat(multinode): add groundwork for multinode support without ray by @​Jooho in #​5366
• fix: upgrade vLLM to 0.19.0 by @​cjohannsen-cloudera in #​5367
• fix: enforce PSS restricted profile on LLMInferenceService default template by @​alokdangre in #​5302
• fix: recover multi download flag in default CSC by @​israel-hdez in #​5368
• fix(agent): mirror user-defined httpGet path onto agent readiness probe by @​reyshazni in #​5345
• fix(llmisvc): shorten webhook name to comply with 63-char label limit by @​spolti in #​5381
• fix: CVE-2026-33186 gRPC authorization bypass by @​sivanantha321 in #​5342
• docs: fix typo in OpenShift guide by @​iranzo in #​5197
• revert(llmisvc): restore original webhook names, reverts #​5381 by @​bartoszmajsak in #​5398
• fix: intermittent 403 Forbidden errors during S3 model download by @​agoston in #​5393
• feat(llmisvc): add SectionName support to Gateway refs by @​bartoszmajsak in #​5410
• build: add GOTAGS build arg to manager and agent Dockerfiles by @​bartoszmajsak in #​5403
• refactor(test): migrate credentials suite to NewEnvTest by @​bartoszmajsak in #​5397
• fix: address CVE-2026-30922: pyasn1 Vulnerable to DoS by @​spolti in #​5404
• feat(release): add Copilot CLI release automation by @​Jooho in #​5419
• release: prepare release v0.18.0-rc0 by @​Jooho in #​5422
• release: prepare release v0.18.0-rc1 by @​Jooho in #​5435
• release: prepare release v0.18.0 by @​Jooho in #​5462

New Contributors

• @​fyuan1316 made their first contribution in #​5167
• @​seBasKov made their first contribution in #​4573
• @​Gregory-Pereira made their first contribution in #​5304
• @​SebastienSyd made their first contribution in #​5199
• @​Yuuuuuu0319 made their first contribution in #​5244
• @​sophieliu15 made their first contribution in #​5313
• @​RishabhSaini made their first contribution in #​5291
• @​alokdangre made their first contribution in #​5302
• @​reyshazni made their first contribution in #​5345
• @​iranzo made their first contribution in #​5197

Full Changelog: kserve/kserve@v0.17.0...v0.18.0

v0.17.0

Compare Source

Installation

• Installation Guide

Breaking Change

• Major Helm Chart Restructuring

What's Changed

• choir: fix missing markers by @​Jooho in #​4793
• fix: update base image for PMML to use eclipse-temurin JDK by @​sivanantha321 in #​4794
• add suffix kserve for helm chart of llmisvc by @​Jooho in #​4792
• Parallelize blob downloads from azure in storage-initializer by @​agoston in #​4709
• Parallelize blob downloads from S3 in storage-initializer by @​agoston in #​4714
• chore: bump k8s package versions to v0.34.0 by @​murataslan in #​4713
• Prevent path traversal on https.go by @​spolti in #​4796
• Refactor existing script to use centralized installation scripts by @​Jooho in #​4787
• fix: CI failure caused by deprecated MinIO image by @​Jooho in #​4812
• feat: Add a python script to generate quick install script by @​Jooho in #​4806
• fix generator to be executable without cloning repo by @​Jooho in #​4813
• Fixing LLMISVC CRD Installation Paths by @​brettmthompson in #​4811
• feat: Add pathTemplate configuration for inference service routing by @​DeepFlame-JR in #​4817
• helmchart: add image pull policy for serving runtimes by @​stergem in #​4814
• fix: multiple storage uri volume mount error by @​sivanantha321 in #​4822
• Fix Bug in LLMISVC E2E Test Setup by @​brettmthompson in #​4841
• fix: Fix various bugs in quickstart scripts by @​JonahSussman in #​4832
• Pin starlette to version 0.49.1 to fix CVE-2025-62727 by @​hdefazio in #​4846
• fix(llmisvc): adds missing generated clients by @​bartoszmajsak in #​4849
• Change security mailing list email address by @​terrytangyuan in #​4853
• Allow stopping LLMInferenceService by @​pierDipi in #​4839
• Add cjohannsen-cloudera as a reviewer by @​terrytangyuan in #​4854
• update go version to 1.25 and kubebuilder version to 1.9.0 by @​Jooho in #​4862
• fix: remove cert-manager annotation in inferenceservice crd by @​juhyeon-cha in #​4837
• update kserve version and update helm chart name by @​Jooho in #​4860
• fix: Address CVE-2025-22872, CVE-2025-47914, CVE-2025-58181 by @​sivanantha321 in #​4866
• Add Support For Protocol in S3 Endpoint by @​brettmthompson in #​4797
• fix: llmisvc image patch script to use renamed manager yaml file by @​sivanantha321 in #​4820
• fix make deploy target in makefile by @​Jooho in #​4872
• ci: add manual trigger for helm publish workflow by @​sivanantha321 in #​4873
• docs: Update KServe diagram to use the KubeCon NA version by @​terrytangyuan in #​4877
• CVE-2024-43598: Update lightgbm version to 4.6.0 by @​sivanantha321 in #​4799
• fix: the quick install scripts temporarily. by @​Jooho in #​4880
• mock test for ray by @​Jooho in #​4885
• fix: synced kserve-helm.sh and kserve-kustomize.sh by @​Jooho in #​4891
• fix: update LWS version to 0.7.0 to fix multi-node E2E test failure by @​vivekk16 in #​4892
• OCI model storage is not working with multi-node feature by @​spolti in #​4889
• Follow up 4787 by @​Jooho in #​4810
• Fix CI precommit error by @​andyi2it in #​4897
• fix: clear stale router and scheduler conditions on config changes by @​vivekk16 in #​4876
• feat: bump up vllm version to 0.11.2 & remove python 3.9 support by @​csy1204 in #​4851
• Remove deprecated --disable-log-requests flag for vLLM 0.11 compatibility by @​vivekk16 in #​4883
• Improved CA Bundle Management For LLM Inference Services by @​brettmthompson in #​4803
• ci: split KServe and Storage publish workflow into separate jobs by @​sivanantha321 in #​4801
• chore: Add .gitattributes to mark vendored and generated code by @​terrytangyuan in #​4904
• ci: add retry request for e2e tests to reduce transient failures by @​sivanantha321 in #​4795
• Address several CVEs by @​spolti in #​4912
• fix: make deploy-dev for development env by @​Jooho in #​4881
• Add precommit check to sync golangci Go version with go.mod by @​Jooho in #​4930
• refactor: replace bash script with Python and improve generate-version by @​Jooho in #​4935
• Fix: opentelemetry helm installation script by @​Jooho in #​4932
• chore: bump github.com/kedacore/keda/v2 from 2.16.1 to 2.17.3 by @​jlost in #​4927
• CVE-2025-66418 - Unbounded number of links in the decompression chain by @​spolti in #​4928
• Fix: LLMInferenceService reconciliation for Gateway refs in baseRefs by @​vivekk16 in #​4944
• Fix: use correct image tag in LLMISvc E2E workflow by @​pierDipi in #​4948
• refactor: deduplicate test configs with helper functions by @​Jooho in #​4952
• Fix CVE-2025-68156: Update expr-lang/expr to v1.17.7 by @​mholder6 in #​4934
• Separate LocalModelCache webhook from KServe controller. by @​Jooho in #​4941
• Bump Gateway API Inference Extension (GIE) to v1.2.0 by @​sbekkerm in #​4886
• feat: add automatic modelFormat annotation for InferenceServices by @​Jooho in #​4953
• AIOHTTP's HTTP Parser auto_decompress feature is vulnerable to zip bomb by @​spolti in #​4939
• ci: PR style check by @​sivanantha321 in #​4499
• add openvino model server runtime by @​dtrawins in #​4592
• feat: add enqueueOnHttpRouteChange handler by @​vivekk16 in #​4955
• feat: add LLMInferenceService CRD webhook + E2E tests by @​KillianGolds in #​4967
• fix: watch pod init container status changes by @​jlost in #​4910
• ci: centralize image variables by @​Jooho in #​4969
• refactor: restructure manifests with component-based by @​Jooho in #​4962
• feat: add predictive inference server runtime by @​Jooho in #​4954
• feat: add predictiveserver runtime build/publish gitaction by @​Jooho in #​4974
• fix: path traversal vulnerability in extractTarFiles by @​sivanantha321 in #​4975
• feat: allow llmisvc scheduler config using a CM or inline by @​pierDipi in #​4856
• fix: add the (default) zmq port 5557 to scheduler by @​pierDipi in #​4964
• feat: add predictiveserver runtime e2e test by @​Jooho in #​4973
• fix: use existing serviceAccount when specified by @​cyon13 in #​4913
• fix: makefile target 'deploy-dev' by @​Jooho in #​4993
• docs: add contributor graph to README by @​terrytangyuan in #​4991
• fix: update envoy ai gateway installation script by @​Jooho in #​4978
• refactor: interface + factory pattern for reconcilers by @​rajatvig in #​4922
• fix: update precise prefix routing example by @​pierDipi in #​5004
• feat: llmisvc preserves externally managed replicas by @​pierDipi in #​4996
• rm cleanHeadSvc from service reconciler by @​cjackal in #​4758
• fix: removed GIE crd from llmisvc kustomzation/Makefile by @​Jooho in #​4997
• fix: resolve flaky TestServerTimeout race condition by @​jlost in #​5001
• feat: update llmisvc e2e test environment script by @​Jooho in #​4999
• refactor: add prefix 'kserve' for llmisvc role by @​Jooho in #​4992
• feat: added git download support to storage initializer by @​agoston in #​4966
• feat: replace minio with seaweedfs by @​Jooho in #​5014
• ci: Add charts/kserve-llmisvc-resources to workflow paths by @​terrytangyuan in #​5027
• fix: llmisvc ClusterRoleBinding to point to new ClusterRole by @​pierDipi in #​5022
• fix: yq download issue & resolving pseudo-versions by @​Jooho in #​5023
• feat(llmisvc): inferencePool auto-migration by @​KillianGolds in #​5007
• feat: make LLMInferenceService storageInitializer optional by @​cabrinha in #​4970
• fix(build): enforce local yq installation by @​bartoszmajsak in #​5046
• fix(build): remove GOPATH dependency from OpenAPI script by @​bartoszmajsak in #​5045
• chore: migrate flake to ruff by @​moulin-louis in #​4981
• feat(llmisvc): move vLLM args to command field by @​KillianGolds in #​5049
• chore(pytest): replaces deprecated get_event_loop by @​bartoszmajsak in #​5066
• fix: h11 accepts malformed bodies - CVE-2025-43859 by @​sivanantha321 in #​5040
• fix: incl. port 8080 in status.address.url for headless svcs by @​jlost in #​4998
• fix: improve storage-initializer error messages by @​mwaykole in #​5016
• fix: make Uvicorn event loop configurable by @​joshyjoseph in #​4971
• feat(llmisvc): watch pods for init container failures by @​jlost in #​5034
• fix: normalize deprec. deploymentMode annos; allow deletion by @​jlost in #​5025
• chore: add pierdipi to reviewers by @​pierDipi in #​5081
• fix: avoid storage-initializer rollout on operator upgrade by @​bartoszmajsak in #​5085
• feat: route only completions through InferencePool by @​bartoszmajsak in #​5087
• feat(llmisvc): listener hostname fallback for URL discovery by @​bartoszmajsak in #​5079
• fix(llmisvc): allow custom gateway with managed route by @​bartoszmajsak in #​5075
• refactor(llmisvc): centralize test namespace management by @​bartoszmajsak in #​5077
• fix(llmisvc): readiness logic for multiple ctrl statuses by @​bartoszmajsak in #​5055
• test: remove blanket sleeps from E2E test utilities by @​bartoszmajsak in #​5071
• fix: broken go tests by @​sivanantha321 in #​5091
• fix(build): upgrade golangci-lint to v2.9.0 by @​bartoszmajsak in #​5072
• feat: 5024 - Upgrade to Gateway API v1.4.0 by @​cjohannsen-cloudera in #​5038
• fix(llmisvc): use server state for Delete owner verification by @​bartoszmajsak in #​5088
• chore(scripts): makes script worktree-friendly by @​bartoszmajsak in #​5069
• fix(inferenceservice): skip VS if Istio CRD missing by @​Siva-Sainath in #​4985
• fix(localmodel): use ObjectOld in node update predicate by @​tmvfb in #​5095
• feat(llmisvc): propagate Prometheus annotations to workloads by @​bartoszmajsak in #​5086
• chore: change 'owners' to 'project-leads' in OWNERS file by @​terrytangyuan in #​5100
• feat: llmisvc supports scaling and HA for scheduler by @​pierDipi in #​5032
• feat: faster parallel S3 file downloads by @​bluayer in #​5102
• feat(llmisvc): add DNS/IP SAN & renewal to self-signed certs by @​bartoszmajsak in #​5099
• feat: inf. log batching, external marshalling support by @​cjohannsen-cloudera in #​5061
• feat(llmisvc): add versioned well-known config resolution by @​bartoszmajsak in #​5096
• fix(llmisvc): return nil instead of empty InferencePoolSpec by @​bartoszmajsak in #​5108
• fix(llmisvc): handle JSON marshal error in ReplaceVariables by @​bartoszmajsak in #​5109
• chore: update OWNERS file by @​terrytangyuan in #​5112
• fix(llmisvc): restricts GlobalConfig fields for templates by @​bartoszmajsak in #​5111
• fix(llmisvc): return error from selectListener on mismatch by @​bartoszmajsak in #​5105
• feat: include all required files to installation script by @​Jooho in #​5103
• fix: surface failure conditions in InferenceService status by @​houshengbo in #​5114
• fix(llmisvc): unblocks certificate renewal by @​bartoszmajsak in #​5106
• feat: new env var INFERENCE_SERVICE_NAME by @​dkoder20 in #​5013
• fix: skip validation for empty modelcar fields by @​bartoszmajsak in #​5083
• fix: add no-cache option for generate-versions-from-gomod.py by @​Jooho in #​5123
• fix(llmisvc): preserve SchedulerConfigSpec conversion by @​bartoszmajsak in #​5110
• feat(llmisvc): add startupProbe to vLLM containers by @​KillianGolds in #​5063
• feat: allow storage init to download only selected files by @​pierDipi in #​5119
• feat: add schedulerName field to ServingRuntimePodSpec by @​Jooho in #​5073
• fix(isvc): preserve reason/message on true conditions by @​Siva-Sainath in #​5129
• ci: add workflow to check if tests are passed before merge by @​sivanantha321 in #​5092
• ci: bump k8s & minikube version by @​sivanantha321 in #​5125
• feat: make agent container resources configurable by @​samuelkim7 in #​5127
• feat: add annotation-based runtime defaults for MLServer by @​Jooho in #​5064
• feat: upgrade VLLM open source version to 0.15.1 by @​cjohannsen-cloudera in #​5098
• test: harden patch-update E2E tests by @​bartoszmajsak in #​5065
• feat: restructure helm charts and the way how to patch by @​Jooho in #​5089
• feat(llmisvc): enhance Gateway API URL discovery by @​bartoszmajsak in #​5104
• fix: resolve CVE-2026-26007 cryptography subgroup attack by @​spolti in #​5151
• feat(llmisvc): enable label/annotation propagation by @​khushiiagrawal in #​5009
• fix: generate OpenAPI and Python SDK models for v1alpha2 LLMISVC by @​bartoszmajsak in #​5152
• feat(llmisvc): add autoscaling API with WVA support by @​vivekk16 in #​5130
• docs: Mention vLLM and llm-d in README by @​terrytangyuan in #​5160
• fix: respect user logging config in kserve (#​3919) by @​KageRyo in #​4687
• fix(llmisvc): change TLS cert mount path to avoid CA bundle conflict by @​bartoszmajsak in #​5157
• feat: preserves scheduler config and restart on cert rotation by @​bartoszmajsak in #​5084
• test: automatic envtest cleanup and suite alignment by @​bartoszmajsak in #​5068
• feat: 5235 update knative-serving to v1.21.1 by @​cjohannsen-cloudera in #​5136
• fix: cve-2026-24486: python-multipart arbitrary file write by @​spolti in #​5170
• fix: uv dead lock issue between kserve and kserve-storage by @​Jooho in #​5176
• fix: update manifests for release by @​Jooho in #​5177
• feat: improve KServe release automation and simplify workflow by @​Jooho in #​5184
• release: prepare release v0.17.0-rc0 by @​Jooho in #​5185
• fix: skip _folder to package helm chart (#​5186) by @​Jooho in #​5189
• refactor: change kserve chart name to kserve-resources (#​5190) by @​Jooho in #​5192

New Contributors

• @​agoston made their first contribution in #​4709
• [

✂ Note

PR body was truncated to here.

---

Configuration

📅 Schedule: (UTC)

• Branch creation
  • At any time (no schedule defined)
• Automerge
  • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

---

• If you want to rebase/retry this PR, check this box

---

This PR was generated by Mend Renovate. View the repository job log.