Release v0.5.0

What's Changed

• Update installation guide by @liurupeng in #217
• Bump the kubernetes group with 5 updates by @dependabot in #224
• Add support to install lws at an arbitrary namespace by @kerthcet in #226
• feat: add build arg to docker buildx by @vie-serendipity in #227
• Injecting TPU_NAME environment variable by @Edwinhr716 in #209
• Creating new workerStatefulSet instead of patching when updating LWS template by @Edwinhr716 in #229
• Update KEP #173 to reflect implementation by @Edwinhr716 in #233
• Add cherry-pick script by @liurupeng in #235
• Add vLLM TPU Multihost example by @Edwinhr716 in #234
• Bump the kubernetes group with 5 updates by @dependabot in #241
• Bump sigs.k8s.io/controller-runtime from 0.19.0 to 0.19.1 by @dependabot in #242
• Changed log level to 2 by @Edwinhr716 in #244
• Bump github.com/onsi/ginkgo/v2 from 2.20.2 to 2.21.0 by @dependabot in #245
• Bump github.com/onsi/gomega from 1.34.2 to 1.35.1 by @dependabot in #246
• change to not use NetworkConfig in hash calculation if it has default value by @Edwinhr716 in #250
• Added validation for subdomainPolicy values by @Edwinhr716 in #251
• changed cherry pick script to be executable by @Edwinhr716 in #253
• add pods finalizer update rbac to allow lws to run in openshift by @kannon92 in #249
• Update installation instructions for release 0.4.2 by @ahg-g in #255
• Bump github.com/open-policy-agent/cert-controller from 0.11.0 to 0.12.0 by @dependabot in #256
• Bump sigs.k8s.io/structured-merge-diff/v4 from 4.4.1 to 4.4.3 by @dependabot in #258
• Unify Leader Election Namespace with Deployment Namespace by @wqlparallel in #263
• Bump github.com/onsi/gomega from 1.35.1 to 1.36.0 by @dependabot in #271
• Added validation for LWS Name by @Edwinhr716 in #272
• Updating OWNERS file by @Edwinhr716 in #273
• Bump github.com/onsi/ginkgo/v2 from 2.21.0 to 2.22.0 by @dependabot in #269
• Bump sigs.k8s.io/controller-runtime from 0.19.1 to 0.19.2 by @dependabot in #270
• Bump the kubernetes group with 5 updates by @dependabot in #268
• Bump sigs.k8s.io/controller-runtime from 0.19.2 to 0.19.3 by @dependabot in #278
• update golang to 1.23 and fix docker warnings by @kannon92 in #279
• Use the namespace of the service account by @kannon92 in #282
• Bump the kubernetes group with 5 updates by @dependabot in #286
• Bump sigs.k8s.io/structured-merge-diff/v4 from 4.4.3 to 4.5.0 by @dependabot in #287
• Bump github.com/onsi/gomega from 1.36.0 to 1.36.1 by @dependabot in #288
• add doc to say how to install in a different namespace by @kannon92 in #285
• Add helm charts for lws. by @wqlparallel in #266
• add KEP 238, to add controller revision by @Edwinhr716 in #261
• address non linear parsing cve by upgrading golang net by @kannon92 in #290
• Bump github.com/onsi/ginkgo/v2 from 2.22.0 to 2.22.1 by @dependabot in #292
• Remove namespace arg from manager command by @chiragjn in #293
• Add Controller Revision (Implementation of KEP #238) by @Edwinhr716 in #277
• Bump github.com/onsi/gomega from 1.36.1 to 1.36.2 by @dependabot in #295
• Tests for Controller Revision by @Edwinhr716 in #297
• Minimize number of unnecessary logs by @Edwinhr716 in #298
• Update Reference Doc by @Edwinhr716 in #300
• Updating owners by @Edwinhr716 in #301
• Add Events by @Edwinhr716 in #299
• Bump github.com/onsi/ginkgo/v2 from 2.22.1 to 2.22.2 by @dependabot in #303
• Replaced Kueue with LWS on chart/lws ReadMe by @Edwinhr716 in #305
• Ignore not found error when handling ReacreateGroupOnPodRestart by @Edwinhr716 in #304
• Replace kube-rbac-proxy by @anshuman-agarwala in #284
• Fixed flaky ControllerRevision test and add CR events by @Edwinhr716 in #306
• Fixed metrics service port, added log level flag back by @Edwinhr716 in #307
• Removed kube-rbac-proxy container from helm charts by @Edwinhr716 in #308

New Contributors

• @vie-serendipity made their first contribution in #227
• @wqlparallel made their first contribution in #263
• @chiragjn made their first contribution in #293
• @anshuman-agarwala made their first contribution in #284

Full Changelog: v0.4.0...v0.5.0

0.4.2

What's Changed

• Automated cherry pick of #250: change to not use NetworkConfig in hash calculation if it has default value by @Edwinhr716 in #252

Full Changelog: v0.4.1...v0.4.2

LeaderWorkerSet Patch release 0.4.1

This is a patch release for v0.4.0

Leaderworkerset v0.4.0

Features:

• Support specify NetworkConfig
• Support leader elect for lws controller
• Add group size as an environment variable
• Add an example for using llama.cpp to deploy a distributed inference service
• Update the GPU multi-node inference with vLLM example to serve Llama3.1-405b model

What's Changed

• Update the lws version of the installation guide by @liurupeng in #160
• Bump the kubernetes group with 6 updates by @dependabot in #165
• add leader elect args by @gujingit in #163
• Add executable permission to the example script ray_init.sh by @xgchena in #166
• docs: add LeaderWorkerSet API reference by @zmvictor in #171
• Bump the kubernetes group with 6 updates by @dependabot in #175
• Add example for llama.cpp by @justinsb in #174
• statefulset finalizer rbac update by @kannon92 in #176
• add verify job and fix code where it fails by @kannon92 in #180
• Bump github.com/onsi/gomega from 1.33.1 to 1.34.0 by @dependabot in #181
• set golangci-lint for 15 minutes to be same as jobset by @kannon92 in #183
• Bump github.com/onsi/ginkgo/v2 from 2.19.0 to 2.19.1 by @dependabot in #182
• Fix missing startupPolicy in applyConfiguration by @kerthcet in #186
• Bump github.com/onsi/gomega from 1.34.0 to 1.34.1 by @dependabot in #187
• updating vllm docs to use llama3 405B as example by @Edwinhr716 in #185
• No worker sts when size=1 by @kerthcet in #190
• Bump cert-controller to v0.11.0 by @kerthcet in #191
• Bump github.com/onsi/ginkgo/v2 from 2.19.1 to 2.20.0 by @dependabot in #192
• add golangci config to project by @kannon92 in #194
• Headless Service Per Replica KEP by @Edwinhr716 in #188
• fix make generate by @kerthcet in #196
• Bump the kubernetes group with 6 updates by @dependabot in #198
• We should not import from k8s/kubernetes. by @kannon92 in #200
• Updated vLLM yaml example to use LWS_LEADER_ADDRESS by @Edwinhr716 in #202
• Bump github.com/onsi/ginkgo/v2 from 2.20.0 to 2.20.1 by @dependabot in #201
• Bump github.com/onsi/gomega from 1.34.1 to 1.34.2 by @dependabot in #205
• Bump github.com/onsi/ginkgo/v2 from 2.20.1 to 2.20.2 by @dependabot in #206
• Bump kubernetes dependencies to v0.31.x. by @mbobrovskyi in #207
• feature: Add group size environment variable injection by @googs1025 in #208
• simply llama.cpp example by @carlory in #212
• Make llama.cpp example become avaliable on macOS by @carlory in #211
• Adding SubdomainPolicy to support a service per replica by @Edwinhr716 in #197
• Deprecated DefaultRestartPolicy with NoneRestartPolicy by @kerthcet in #214

New Contributors

• @xgchena made their first contribution in #166
• @zmvictor made their first contribution in #171
• @justinsb made their first contribution in #174
• @mbobrovskyi made their first contribution in #207
• @carlory made their first contribution in #212

Full Changelog: v0.3.0...v0.4.0

Leaderworkerset v0.3.0

Features:

• RollingUpdate with MaxSurge support
• Subgroup support for disaggregated serving
• Example for multi-node serving of llama 70B on GPUs with vLLM
• Add a new start policy API
• Inject leader address environment variable to every container
• Spec.rolloutStrategy should be a non-required field

Acknowledgments

Thanks to our contributors in this release, in alphabetic order:
@ahg-g @Edwinhr716 @googs1025 @gujingit @jjk-g @kerthcet @liurupeng @nayihz

Leaderworkerset v0.2.0

Features:

• Support RollingUpdate with MaxUnavailable
• Allow Prometheus to gather metrics gathered by controller-runtime
• Fix TPU env var assignment when leader pod doesn't request TPU
• User guide to deploy multi-host inference with Saxml
• Increase qps limit for pod scheduling
• Setup E2E test and improve test coverage

Acknowledgments

Thanks to our contributors in this release, in alphabetic order:
@ahg-g @Bslabe123 @Edwinhr716 @googs1025 @kannon92 @kerthcet @liurupeng @nayihz @Zeel-Patel

Leaderworkerset v0.1.0

Features:

• Support creating groups of pods as a unit
• Support dual-template, one for leader and one for the workers
• Support autoscaling through HPA
• Support topology-aware placement
• Support all-or-nothing restart for failure handling

Acknowledgments

Thanks to our contributors in this release, in no particular order:
@liurupeng @Edwinhr716 @kerthcet @ahg-g