v0.4.0

Docker image is available at:

docker pull ghcr.io/llm-d/llm-d-inference-scheduler:v0.4.0

What's Changed

• Use a production version of Istio by @shmuelk in #334
• add vMaroon as code owner by @elevran in #342
• Upgrade github.com/llm-d/llm-d-kv-cache-manager import to v0.3.0 by @vMaroon in #344
• add a hold label when PRs are pushed to branch other than main by @nirrozenbaum in #345
• sync gic to latest v1.0.0 release by @nirrozenbaum in #353
• deps(actions): bump actions/stale from 9 to 10 by @dependabot[bot] in #350
• deps(actions): bump actions/setup-go from 5 to 6 by @dependabot[bot] in #351
• deps(actions): bump crate-ci/typos from 1.35.7 to 1.36.2 by @dependabot[bot] in #348
• deps(go): bump the go-dependencies group with 7 updates by @dependabot[bot] in #349
• bump llm-d-kv-cache-manager version by @vMaroon in #359
• fix: Rename config to kv-cache-utilization-scorer from kv-cache-scorer by @yankay in #358
• updating release issue-template by @kfswain in #361
• bump llm-d-kv-cache-manager version (v0.3.2) by @vMaroon in #365
• deps(go): bump github.com/onsi/ginkgo/v2 from 2.25.3 to 2.26.0 in the go-dependencies group by @dependabot[bot] in #368
• feat: Add a scoring plugin to distribute new groups evenly by @usize in #357
• implement PreRequest and PostResponse interface checks by @learner0810 in #372
• deps(go): bump the kubernetes group with 2 updates by @dependabot[bot] in #369
• deps(go): bump google.golang.org/grpc from 1.75.1 to 1.76.0 in the go-dependencies group by @dependabot[bot] in #374
• Supports the ResponseComplete plugin by @learner0810 in #378
• deps(actions): bump crate-ci/typos from 1.36.2 to 1.38.1 by @dependabot[bot] in #373
• Fix multi-architecture image issues with Kind by @shmuelk in #362
• feat: Moved the Routing Sidecar from its own repo to the inference-scheduler repo by @shmuelk in #379
• Upgrade to use Gateway Inference Extension 1.1.0 rc.1 by @shmuelk in #384
• deps(go): bump github.com/onsi/ginkgo/v2 from 2.26.0 to 2.27.1 in the go-dependencies group by @dependabot[bot] in #389
• Ensure that max_completion_tokens=1 in Prefill by @shmuelk in #403
• Add explanation of inference-scheduler relation to IGW/GIE by @elevran in #393
• Add test coverage to test-unit Makefile target by @carlory in #391
• Add regression tests for max_completion_tokens by @pierDipi in #411
• Makefile refactoring to minimize the number of targets by @shmuelk in #397
• feat: Add vLLM Data Parallel support to llm-d-inference-scheduler by @shmuelk in #392
• fix(scorer): prevent potential division by zero in ActiveRequest.Score by @googs1025 in #413
• Fixed wildcard targets by @shmuelk in #416
• deps(actions): bump crate-ci/typos from 1.38.1 to 1.39.0 by @dependabot[bot] in #419
• deps(go): bump github.com/onsi/ginkgo/v2 from 2.27.1 to 2.27.2 in the go-dependencies group by @dependabot[bot] in #417
• Missed change to the Go code coverage output file names in the Makefile refactoring by @shmuelk in #422
• Fix: Remove reference to the missing make target by @andreyod in #423
• deps(actions): bump actions/upload-artifact from 4 to 5 by @dependabot[bot] in #420
• deps(go): bump sigs.k8s.io/controller-runtime from 0.22.3 to 0.22.4 in the kubernetes group by @dependabot[bot] in #418
• Enhancement: return 503 instead of 502 when decode node is not ready by @Phil-OSophy-42 in #412
• Remove endpointslices from RBAC by @elevran in #424
• Fix Image Loading for Podman in E2E Tests by @hdefazio in #406
• readme meetings update by @nirrozenbaum in #427
• Fix references to the SideCar's tag by @shmuelk in #428
• Remove duplicate error logs by @hyeongyun0916 in #429
• Upgrade to istio-1.28 by @irar2 in #431
• Complete upgrade to Istio 1.28.0 by @shmuelk in #433
• Upgrade GIE dependency to 1.1.0 by @shmuelk in #435
• Remove dev from branch list in PR actions by @elevran in #434
• Added support for Data Parallel in a Disagregated Prefil/Decode setup by @shmuelk in #432
• Remove code coverage from CI workflow by @carlory in #437
• test: Scale up and down the model server during an end to end test by @shmuelk in #354
• fix: add validation in ByLabelFactory to prevent invalid configurations by @googs1025 in #440
• deps(actions): bump golangci/golangci-lint-action from 8 to 9 by @dependabot[bot] in #444
• change lmcache connector to nixlv2 by @googs1025 in #446
• fix: Roll back automatic updates to Dockerfiles by @shmuelk in #447
• deps(go): bump golang.org/x/sync from 0.17.0 to 0.18.0 in the go-dependencies group by @dependabot[bot] in #443
• fix(profile): validate handler parameters to prevent invalid config by @googs1025 in #449
• Added chat completions preprocessing support by @guygir in #426
• docs: add integration guide for external prefill/decode workloads by @googs1025 in #451
• Define and manage PR lifecycle by @elevran in #450
• test: End to End test for Data Parallel support by @shmuelk in #442
• docs: add PD-aware examples for by-label and by-label-selector plugins by @googs1025 in #454
• deps(actions): bump crate-ci/typos from 1.39.0 to 1.39.2 by @dependabot[bot] in #459
• Add SGLang Connector for Prefill/Decode Disaggregation (migrated from llm-d-routing-sidecar#64) by @bongwoobak in #456
• deps(go): bump the kubernetes group with 4 updates by @dependabot[bot] in #460
• add unit test in scheduler plugin part(by-label, data-parallel-profile-handler, pd-profile-handler) by @googs1025 in #461
• test: Enable running the end to end tests on K8S clusters other than Kind by @shmuelk in #453
• Allow the sidecar to sample from a list of prefill host ports by @smarterclayton in #404
• fix: Fixed issues running locally 'make lint' and 'make test-unit' by @shmuelk in #464
• cleanup: Followup to Python paths fix by @shmuelk in #468
• Replace tab with spaces to avoid treating as make target by @elevran in #469
• minor refactoring of precise-prefix-cache scorer plugin by @vMaroon in #473
• feat: Add initial metrics and update dependencies by...

v0.4.0-rc.1

Docker image is available here:

docker pull ghcr.io/llm-d/llm-d-inference-scheduler:v0.4.0-rc.1

What's Changed

• Use a production version of Istio by @shmuelk in #334
• add vMaroon as code owner by @elevran in #342
• Upgrade github.com/llm-d/llm-d-kv-cache-manager import to v0.3.0 by @vMaroon in #344
• add a hold label when PRs are pushed to branch other than main by @nirrozenbaum in #345
• sync gic to latest v1.0.0 release by @nirrozenbaum in #353
• deps(actions): bump actions/stale from 9 to 10 by @dependabot[bot] in #350
• deps(actions): bump actions/setup-go from 5 to 6 by @dependabot[bot] in #351
• deps(actions): bump crate-ci/typos from 1.35.7 to 1.36.2 by @dependabot[bot] in #348
• deps(go): bump the go-dependencies group with 7 updates by @dependabot[bot] in #349
• bump llm-d-kv-cache-manager version by @vMaroon in #359
• fix: Rename config to kv-cache-utilization-scorer from kv-cache-scorer by @yankay in #358
• updating release issue-template by @kfswain in #361
• bump llm-d-kv-cache-manager version (v0.3.2) by @vMaroon in #365
• deps(go): bump github.com/onsi/ginkgo/v2 from 2.25.3 to 2.26.0 in the go-dependencies group by @dependabot[bot] in #368
• feat: Add a scoring plugin to distribute new groups evenly by @usize in #357
• implement PreRequest and PostResponse interface checks by @learner0810 in #372
• deps(go): bump the kubernetes group with 2 updates by @dependabot[bot] in #369
• deps(go): bump google.golang.org/grpc from 1.75.1 to 1.76.0 in the go-dependencies group by @dependabot[bot] in #374
• Supports the ResponseComplete plugin by @learner0810 in #378
• deps(actions): bump crate-ci/typos from 1.36.2 to 1.38.1 by @dependabot[bot] in #373
• Fix multi-architecture image issues with Kind by @shmuelk in #362
• feat: Moved the Routing Sidecar from its own repo to the inference-scheduler repo by @shmuelk in #379
• Upgrade to use Gateway Inference Extension 1.1.0 rc.1 by @shmuelk in #384
• deps(go): bump github.com/onsi/ginkgo/v2 from 2.26.0 to 2.27.1 in the go-dependencies group by @dependabot[bot] in #389
• Ensure that max_completion_tokens=1 in Prefill by @shmuelk in #403
• Add explanation of inference-scheduler relation to IGW/GIE by @elevran in #393
• Add test coverage to test-unit Makefile target by @carlory in #391
• Add regression tests for max_completion_tokens by @pierDipi in #411
• Makefile refactoring to minimize the number of targets by @shmuelk in #397
• feat: Add vLLM Data Parallel support to llm-d-inference-scheduler by @shmuelk in #392
• fix(scorer): prevent potential division by zero in ActiveRequest.Score by @googs1025 in #413
• Fixed wildcard targets by @shmuelk in #416
• deps(actions): bump crate-ci/typos from 1.38.1 to 1.39.0 by @dependabot[bot] in #419
• deps(go): bump github.com/onsi/ginkgo/v2 from 2.27.1 to 2.27.2 in the go-dependencies group by @dependabot[bot] in #417
• Missed change to the Go code coverage output file names in the Makefile refactoring by @shmuelk in #422
• Fix: Remove reference to the missing make target by @andreyod in #423
• deps(actions): bump actions/upload-artifact from 4 to 5 by @dependabot[bot] in #420
• deps(go): bump sigs.k8s.io/controller-runtime from 0.22.3 to 0.22.4 in the kubernetes group by @dependabot[bot] in #418
• Enhancement: return 503 instead of 502 when decode node is not ready by @Phil-OSophy-42 in #412
• Remove endpointslices from RBAC by @elevran in #424
• Fix Image Loading for Podman in E2E Tests by @hdefazio in #406
• readme meetings update by @nirrozenbaum in #427
• Fix references to the SideCar's tag by @shmuelk in #428
• Remove duplicate error logs by @hyeongyun0916 in #429
• Upgrade to istio-1.28 by @irar2 in #431
• Complete upgrade to Istio 1.28.0 by @shmuelk in #433
• Upgrade GIE dependency to 1.1.0 by @shmuelk in #435
• Remove dev from branch list in PR actions by @elevran in #434
• Added support for Data Parallel in a Disagregated Prefil/Decode setup by @shmuelk in #432
• Remove code coverage from CI workflow by @carlory in #437
• test: Scale up and down the model server during an end to end test by @shmuelk in #354
• fix: add validation in ByLabelFactory to prevent invalid configurations by @googs1025 in #440
• deps(actions): bump golangci/golangci-lint-action from 8 to 9 by @dependabot[bot] in #444
• change lmcache connector to nixlv2 by @googs1025 in #446
• fix: Roll back automatic updates to Dockerfiles by @shmuelk in #447
• deps(go): bump golang.org/x/sync from 0.17.0 to 0.18.0 in the go-dependencies group by @dependabot[bot] in #443
• fix(profile): validate handler parameters to prevent invalid config by @googs1025 in #449
• Added chat completions preprocessing support by @guygir in #426
• docs: add integration guide for external prefill/decode workloads by @googs1025 in #451
• Define and manage PR lifecycle by @elevran in #450
• test: End to End test for Data Parallel support by @shmuelk in #442
• docs: add PD-aware examples for by-label and by-label-selector plugins by @googs1025 in #454
• deps(actions): bump crate-ci/typos from 1.39.0 to 1.39.2 by @dependabot[bot] in #459
• Add SGLang Connector for Prefill/Decode Disaggregation (migrated from llm-d-routing-sidecar#64) by @bongwoobak in #456
• deps(go): bump the kubernetes group with 4 updates by @dependabot[bot] in #460
• add unit test in scheduler plugin part(by-label, data-parallel-profile-handler, pd-profile-handler) by @googs1025 in #461
• test: Enable running the end to end tests on K8S clusters other than Kind by @shmuelk in #453
• Allow the sidecar to sample from a list of prefill host ports by @smarterclayton in #404
• fix: Fixed issues running locally 'make lint' and 'make test-unit' by @shmuelk in #464
• cleanup: Followup to Python paths fix by @shmuelk in #468
• Replace tab with spaces to avoid treating as make target by @elevran in #469
• minor refactoring of precise-prefix-cache scorer plugin by @vMaroon in #473
• feat: Add initial metrics and update dependencies...

v0.3.2

In addition to the below changes these patches include fixes to the kv-cache-manager dependency

What's Changed

• bump gie version to v0.5.0 by @nirrozenbaum in #256
• Fixes for Steps to Build a Kubernetes Development Environment by @dumb0002 in #259
• bump gie version to v0.5.1 rc1 (patch release) by @nirrozenbaum in #262
• added badges to readme by @nirrozenbaum in #261
• chore: bump gie version by @nirrozenbaum in #263
• Update prefix-cache-scorer Configuration Doc Entry by @vMaroon in #264
• Update Tokenizer Release Version by @vMaroon in #265
• #245 Followup - Makefile Installs libzmq Dependency by @vMaroon in #266
• deps(go): bump the go-dependencies group with 3 updates by @dependabot[bot] in #257
• Add codespell integration for spell checking by @Jooho in #221
• Initial CODEOWNERS file by @elevran in #267
• added issues templates by @nirrozenbaum in #272
• deps(actions): bump crate-ci/typos from 1.34.0 to 1.35.1 by @dependabot[bot] in #275
• small updates to documentation by @kfswain in #277
• Change CI to only create a latest tagged image on releases by @shmuelk in #278
• fix: correct shell command substitution syntax in Makefile by @yankay in #276
• add reference to writing a new plugin by @elevran in #280
• deps(actions): bump crate-ci/typos from 1.35.1 to 1.35.3 by @dependabot[bot] in #282
• deps(actions): bump actions/checkout from 4 to 5 by @dependabot[bot] in #283
• Remove non-existent labels from dependabot configuration by @elevran in #285
• chore: ⬆️ bump components gie to v0.5.1. by @yafengio in #288
• Add workflows to automate aged issues management by @anoruxylene in #289
• update load aware scorer unit tests by @jairuigou in #291
• Add build metadata to Docker image by @carlory in #292
• Add Prow GitHub Actions by @Jooho in #290
• remove setup log by @carlory in #294
• OWNERS_ALIASES is not working with current automation by @nirrozenbaum in #296
• deps(actions): bump crate-ci/typos from 1.35.3 to 1.35.4 by @dependabot[bot] in #299
• deps(actions): bump actions/checkout from 4 to 5 by @dependabot[bot] in #300
• deps(go): bump the go-dependencies group with 2 updates by @dependabot[bot] in #301
• fix: Makefile fixes for MacOS by @shmuelk in #304
• Update comment in prow-pr-automerge.yml by @elevran in #303
• Remove github CODEOWNERS by @elevran in #306
• deps(docker): bump projectquay/golang from 1.24 to 1.25 by @dependabot[bot] in #302
• Support for installation of inference-sim with kv-cache enabled by @mayabar in #305
• add tokenizer directory to simulator deployment yaml by @mayabar in #307
• [feature] Added Active-Request-Scorer by @vMaroon in #297
• deps(actions): bump crate-ci/typos from 1.35.4 to 1.35.5 by @dependabot[bot] in #316
• deps(go): bump github.com/stretchr/testify from 1.10.0 to 1.11.0 in the go-dependencies group by @dependabot[bot] in #314
• chore: Added end to end tests by @shmuelk in #310
• ByLabelSelector filter tests by @elevran in #315
• chore: drop plugin type from types and file by @yyzxw in #308
• fixed a bug where typos check is checking go.mod and go.sum by @nirrozenbaum in #321
• minor tweaks to Makefile by @nirrozenbaum in #318
• Split the prefix-cache-scorer plugins by @vMaroon in #323
• Makefile fixes by @vMaroon in #322
• deps(actions): bump crate-ci/typos from 1.35.5 to 1.35.7 by @dependabot[bot] in #325
• deps(go): bump the go-dependencies group with 9 updates by @dependabot[bot] in #326
• Reduce img size by cleaning dnf cache by @rawagner in #328
• added comment to stale issues by @nirrozenbaum in #327
• fixed missing dependencies in makefile by @nirrozenbaum in #330
• sync with IGW release 1.0.0-rc by @nirrozenbaum in #320
• fix: make env-dev-kind fails after sync with IGW 1.0.0-rc-3 by @shmuelk in #331

New Contributors

• @dumb0002 made their first contribution in #259
• @yafengio made their first contribution in #288
• @anoruxylene made their first contribution in #289
• @jairuigou made their first contribution in #291
• @yyzxw made their first contribution in #308
• @rawagner made their first contribution in #328

Full Changelog: v0.2.1...v0.3.2

v0.3.2-rc.1

Small fixes to kv-cache-manager required updated dependencies

v0.3.1

Small patch updating kv cache manager dependency to include support in v0.3

See the full v0.3 changes here:

What's Changed

• bump gie version to v0.5.0 by @nirrozenbaum in #256
• Fixes for Steps to Build a Kubernetes Development Environment by @dumb0002 in #259
• bump gie version to v0.5.1 rc1 (patch release) by @nirrozenbaum in #262
• added badges to readme by @nirrozenbaum in #261
• chore: bump gie version by @nirrozenbaum in #263
• Update prefix-cache-scorer Configuration Doc Entry by @vMaroon in #264
• Update Tokenizer Release Version by @vMaroon in #265
• #245 Followup - Makefile Installs libzmq Dependency by @vMaroon in #266
• deps(go): bump the go-dependencies group with 3 updates by @dependabot[bot] in #257
• Add codespell integration for spell checking by @Jooho in #221
• Initial CODEOWNERS file by @elevran in #267
• added issues templates by @nirrozenbaum in #272
• deps(actions): bump crate-ci/typos from 1.34.0 to 1.35.1 by @dependabot[bot] in #275
• small updates to documentation by @kfswain in #277
• Change CI to only create a latest tagged image on releases by @shmuelk in #278
• fix: correct shell command substitution syntax in Makefile by @yankay in #276
• add reference to writing a new plugin by @elevran in #280
• deps(actions): bump crate-ci/typos from 1.35.1 to 1.35.3 by @dependabot[bot] in #282
• deps(actions): bump actions/checkout from 4 to 5 by @dependabot[bot] in #283
• Remove non-existent labels from dependabot configuration by @elevran in #285
• chore: ⬆️ bump components gie to v0.5.1. by @yafengio in #288
• Add workflows to automate aged issues management by @anoruxylene in #289
• update load aware scorer unit tests by @jairuigou in #291
• Add build metadata to Docker image by @carlory in #292
• Add Prow GitHub Actions by @Jooho in #290
• remove setup log by @carlory in #294
• OWNERS_ALIASES is not working with current automation by @nirrozenbaum in #296
• deps(actions): bump crate-ci/typos from 1.35.3 to 1.35.4 by @dependabot[bot] in #299
• deps(actions): bump actions/checkout from 4 to 5 by @dependabot[bot] in #300
• deps(go): bump the go-dependencies group with 2 updates by @dependabot[bot] in #301
• fix: Makefile fixes for MacOS by @shmuelk in #304
• Update comment in prow-pr-automerge.yml by @elevran in #303
• Remove github CODEOWNERS by @elevran in #306
• deps(docker): bump projectquay/golang from 1.24 to 1.25 by @dependabot[bot] in #302
• Support for installation of inference-sim with kv-cache enabled by @mayabar in #305
• add tokenizer directory to simulator deployment yaml by @mayabar in #307
• [feature] Added Active-Request-Scorer by @vMaroon in #297
• deps(actions): bump crate-ci/typos from 1.35.4 to 1.35.5 by @dependabot[bot] in #316
• deps(go): bump github.com/stretchr/testify from 1.10.0 to 1.11.0 in the go-dependencies group by @dependabot[bot] in #314
• chore: Added end to end tests by @shmuelk in #310
• ByLabelSelector filter tests by @elevran in #315
• chore: drop plugin type from types and file by @yyzxw in #308
• fixed a bug where typos check is checking go.mod and go.sum by @nirrozenbaum in #321
• minor tweaks to Makefile by @nirrozenbaum in #318
• Split the prefix-cache-scorer plugins by @vMaroon in #323
• Makefile fixes by @vMaroon in #322
• deps(actions): bump crate-ci/typos from 1.35.5 to 1.35.7 by @dependabot[bot] in #325
• deps(go): bump the go-dependencies group with 9 updates by @dependabot[bot] in #326
• Reduce img size by cleaning dnf cache by @rawagner in #328
• added comment to stale issues by @nirrozenbaum in #327
• fixed missing dependencies in makefile by @nirrozenbaum in #330
• sync with IGW release 1.0.0-rc by @nirrozenbaum in #320
• fix: make env-dev-kind fails after sync with IGW 1.0.0-rc-3 by @shmuelk in #331

New Contributors

• @dumb0002 made their first contribution in #259
• @kfswain made their first contribution in #277
• @yafengio made their first contribution in #288
• @anoruxylene made their first contribution in #289
• @jairuigou made their first contribution in #291
• @yyzxw made their first contribution in #308
• @rawagner made their first contribution in #328

Full Changelog: v0.2.1...v0.3.1

v0.3.1-rc.1

Full Changelog: v0.3.0...v0.3.1-rc.1

v0.3.0

Image pull example: docker pull ghcr.io/llm-d/llm-d-inference-scheduler:v0.3.0

What's Changed

• bump gie version to v0.5.0 by @nirrozenbaum in #256
• Fixes for Steps to Build a Kubernetes Development Environment by @dumb0002 in #259
• bump gie version to v0.5.1 rc1 (patch release) by @nirrozenbaum in #262
• added badges to readme by @nirrozenbaum in #261
• chore: bump gie version by @nirrozenbaum in #263
• Update prefix-cache-scorer Configuration Doc Entry by @vMaroon in #264
• Update Tokenizer Release Version by @vMaroon in #265
• #245 Followup - Makefile Installs libzmq Dependency by @vMaroon in #266
• deps(go): bump the go-dependencies group with 3 updates by @dependabot[bot] in #257
• Add codespell integration for spell checking by @Jooho in #221
• Initial CODEOWNERS file by @elevran in #267
• added issues templates by @nirrozenbaum in #272
• deps(actions): bump crate-ci/typos from 1.34.0 to 1.35.1 by @dependabot[bot] in #275
• small updates to documentation by @kfswain in #277
• Change CI to only create a latest tagged image on releases by @shmuelk in #278
• fix: correct shell command substitution syntax in Makefile by @yankay in #276
• add reference to writing a new plugin by @elevran in #280
• deps(actions): bump crate-ci/typos from 1.35.1 to 1.35.3 by @dependabot[bot] in #282
• deps(actions): bump actions/checkout from 4 to 5 by @dependabot[bot] in #283
• Remove non-existent labels from dependabot configuration by @elevran in #285
• chore: ⬆️ bump components gie to v0.5.1. by @yafengio in #288
• Add workflows to automate aged issues management by @anoruxylene in #289
• update load aware scorer unit tests by @jairuigou in #291
• Add build metadata to Docker image by @carlory in #292
• Add Prow GitHub Actions by @Jooho in #290
• remove setup log by @carlory in #294
• OWNERS_ALIASES is not working with current automation by @nirrozenbaum in #296
• deps(actions): bump crate-ci/typos from 1.35.3 to 1.35.4 by @dependabot[bot] in #299
• deps(actions): bump actions/checkout from 4 to 5 by @dependabot[bot] in #300
• deps(go): bump the go-dependencies group with 2 updates by @dependabot[bot] in #301
• fix: Makefile fixes for MacOS by @shmuelk in #304
• Update comment in prow-pr-automerge.yml by @elevran in #303
• Remove github CODEOWNERS by @elevran in #306
• deps(docker): bump projectquay/golang from 1.24 to 1.25 by @dependabot[bot] in #302
• Support for installation of inference-sim with kv-cache enabled by @mayabar in #305
• add tokenizer directory to simulator deployment yaml by @mayabar in #307
• [feature] Added Active-Request-Scorer by @vMaroon in #297
• deps(actions): bump crate-ci/typos from 1.35.4 to 1.35.5 by @dependabot[bot] in #316
• deps(go): bump github.com/stretchr/testify from 1.10.0 to 1.11.0 in the go-dependencies group by @dependabot[bot] in #314
• chore: Added end to end tests by @shmuelk in #310
• ByLabelSelector filter tests by @elevran in #315
• chore: drop plugin type from types and file by @yyzxw in #308
• fixed a bug where typos check is checking go.mod and go.sum by @nirrozenbaum in #321
• minor tweaks to Makefile by @nirrozenbaum in #318
• Split the prefix-cache-scorer plugins by @vMaroon in #323
• Makefile fixes by @vMaroon in #322
• deps(actions): bump crate-ci/typos from 1.35.5 to 1.35.7 by @dependabot[bot] in #325
• deps(go): bump the go-dependencies group with 9 updates by @dependabot[bot] in #326
• Reduce img size by cleaning dnf cache by @rawagner in #328
• added comment to stale issues by @nirrozenbaum in #327
• fixed missing dependencies in makefile by @nirrozenbaum in #330
• sync with IGW release 1.0.0-rc by @nirrozenbaum in #320
• fix: make env-dev-kind fails after sync with IGW 1.0.0-rc-3 by @shmuelk in #331

New Contributors

• @dumb0002 made their first contribution in #259
• @kfswain made their first contribution in #277
• @yankay made their first contribution in #276
• @yafengio made their first contribution in #288
• @anoruxylene made their first contribution in #289
• @jairuigou made their first contribution in #291
• @yyzxw made their first contribution in #308
• @rawagner made their first contribution in #328

Full Changelog: v0.2.1...v0.3.0

v0.3.0-rc.2

Image is available here: docker pull ghcr.io/llm-d/llm-d-inference-scheduler:v0.3.0-rc.2

v0.3.0-rc.1

Image is available here: docker pull ghcr.io/llm-d/llm-d-inference-scheduler:v0.3.0-rc.1

What's Changed

• bump gie version to v0.5.0 by @nirrozenbaum in #256
• Fixes for Steps to Build a Kubernetes Development Environment by @dumb0002 in #259
• bump gie version to v0.5.1 rc1 (patch release) by @nirrozenbaum in #262
• added badges to readme by @nirrozenbaum in #261
• chore: bump gie version by @nirrozenbaum in #263
• Update prefix-cache-scorer Configuration Doc Entry by @vMaroon in #264
• Update Tokenizer Release Version by @vMaroon in #265
• #245 Followup - Makefile Installs libzmq Dependency by @vMaroon in #266
• deps(go): bump the go-dependencies group with 3 updates by @dependabot[bot] in #257
• Add codespell integration for spell checking by @Jooho in #221
• Initial CODEOWNERS file by @elevran in #267
• added issues templates by @nirrozenbaum in #272
• deps(actions): bump crate-ci/typos from 1.34.0 to 1.35.1 by @dependabot[bot] in #275
• small updates to documentation by @kfswain in #277
• Change CI to only create a latest tagged image on releases by @shmuelk in #278
• fix: correct shell command substitution syntax in Makefile by @yankay in #276
• add reference to writing a new plugin by @elevran in #280
• deps(actions): bump crate-ci/typos from 1.35.1 to 1.35.3 by @dependabot[bot] in #282
• deps(actions): bump actions/checkout from 4 to 5 by @dependabot[bot] in #283
• Remove non-existent labels from dependabot configuration by @elevran in #285
• chore: ⬆️ bump components gie to v0.5.1. by @yafengio in #288
• Add workflows to automate aged issues management by @anoruxylene in #289
• update load aware scorer unit tests by @jairuigou in #291
• Add build metadata to Docker image by @carlory in #292
• Add Prow GitHub Actions by @Jooho in #290
• remove setup log by @carlory in #294
• OWNERS_ALIASES is not working with current automation by @nirrozenbaum in #296
• deps(actions): bump crate-ci/typos from 1.35.3 to 1.35.4 by @dependabot[bot] in #299
• deps(actions): bump actions/checkout from 4 to 5 by @dependabot[bot] in #300
• deps(go): bump the go-dependencies group with 2 updates by @dependabot[bot] in #301
• fix: Makefile fixes for MacOS by @shmuelk in #304
• Update comment in prow-pr-automerge.yml by @elevran in #303
• Remove github CODEOWNERS by @elevran in #306
• deps(docker): bump projectquay/golang from 1.24 to 1.25 by @dependabot[bot] in #302
• Support for installation of inference-sim with kv-cache enabled by @mayabar in #305
• add tokenizer directory to simulator deployment yaml by @mayabar in #307
• [feature] Added Active-Request-Scorer by @vMaroon in #297
• deps(actions): bump crate-ci/typos from 1.35.4 to 1.35.5 by @dependabot[bot] in #316
• deps(go): bump github.com/stretchr/testify from 1.10.0 to 1.11.0 in the go-dependencies group by @dependabot[bot] in #314
• chore: Added end to end tests by @shmuelk in #310
• ByLabelSelector filter tests by @elevran in #315
• chore: drop plugin type from types and file by @yyzxw in #308
• fixed a bug where typos check is checking go.mod and go.sum by @nirrozenbaum in #321
• minor tweaks to Makefile by @nirrozenbaum in #318
• Split the prefix-cache-scorer plugins by @vMaroon in #323
• Makefile fixes by @vMaroon in #322
• deps(actions): bump crate-ci/typos from 1.35.5 to 1.35.7 by @dependabot[bot] in #325
• deps(go): bump the go-dependencies group with 9 updates by @dependabot[bot] in #326
• Reduce img size by cleaning dnf cache by @rawagner in #328
• added comment to stale issues by @nirrozenbaum in #327
• fixed missing dependencies in makefile by @nirrozenbaum in #330
• sync with IGW release 1.0.0-rc by @nirrozenbaum in #320
• fix: make env-dev-kind fails after sync with IGW 1.0.0-rc-3 by @shmuelk in #331

New Contributors

• @dumb0002 made their first contribution in #259
• @kfswain made their first contribution in #277
• @yankay made their first contribution in #276
• @yafengio made their first contribution in #288
• @anoruxylene made their first contribution in #289
• @jairuigou made their first contribution in #291
• @yyzxw made their first contribution in #308
• @rawagner made their first contribution in #328

Full Changelog: v0.2.0-rc.2...v0.3.0-rc.1

v0.2.1

Image is available here: docker pull ghcr.io/llm-d/llm-d-inference-scheduler:v0.2.1

This patch fix is intended to resolve a few bug fixes.
Justification & breakdown here: kubernetes-sigs/gateway-api-inference-extension#1215

• Helm chart configurability: kubernetes-sigs/gateway-api-inference-extension#1211
• TLS metric scraping: kubernetes-sigs/gateway-api-inference-extension#1190
• Fixing max score picker: kubernetes-sigs/gateway-api-inference-extension#1205

Full Changelog: v0.2.0...v0.2.1