v0.14.0

What's Changed

• Prevent the PassthroughCluster for clients/workloads in the service mesh by @israel-hdez in #3711
• Extract openai predict logic into smaller methods by @grandbora in #3716
• Bump MLServer to 1.5.0 by @sivanantha321 in #3740
• Refactor storage initializer to log model download time for all storage types by @sivanantha321 in #3735
• inferenceservice controller: fix error check in Serverless mode by @dtrifiro in #3753
• Add nccl package and Bump vLLM to 0.4.3 for huggingface runtime by @sivanantha321 in #3723
• Propagate trust_remote_code flag throughout vLLM startup by @calwoo in #3729
• Fix dead links on PyPI by @kevinbazira in #3754
• Fix model is ready even if there is no model by @HAO2167 in #3275
• Fix No model ready error in multi model serving by @sivanantha321 in #3758
• Initial implementation of Inference client by @sivanantha321 in #3401
• Fix logprobs for vLLM by @sivanantha321 in #3738
• Fix model name not properly parsed by inference graph by @sivanantha321 in #3746
• pillow - Buffer Overflow by @spolti in #3598
• Use add_generation_prompt while creating chat template by @Datta0 in #3775
• Deduplicate the names for the additional domain names by @houshengbo in #3773
• Make Virtual Service case-insensitive by @andyi2it in #3779
• Install packages needed for vllm model load by @gavrissh in #3802
• Make gRPC max message length configurable by @sivanantha321 in #3741
• Add readiness probe for MLServer and Increase memory for pmml in CI by @sivanantha321 in #3789
• Several bug fixes for vLLM completion endpoint by @sivanantha321 in #3788
• Increase timeout to make unit test stable by @Jooho in #3808
• Upgrade CI deps by @sivanantha321 in #3822
• Add tests for vLLM by @sivanantha321 in #3771
• Bump python to 3.11 for serving runtime images and Bump poetry to 1.8.3 by @sivanantha321 in #3812
• Bump vLLM to 0.5.3.post1 by @sivanantha321 in #3828
• Refactor the ModelServer to let uvicorn handle multiple workers and use 'spawn' for mutiprocessing by @sivanantha321 in #3757
• Update golang for docs/Dockerfile to 1.21 by @spolti in #3761
• Make ray an optional dependency by @sivanantha321 in #3834
• Update aif example by @spolti in #3765
• Use helm for quick installation by @sivanantha321 in #3813
• Allow KServe to have its own local gateways for Serverless mode by @israel-hdez in #3737
• Add support for Azure DNS zone endpoints by @tjandy98 in #3819
• Fix failed build for knativeLocalGatewayService by @yuzisun in #3866
• Add logging request feature for vLLM backend by @sivanantha321 in #3849
• Bump vLLM to 0.5.4 by @sivanantha321 in #3874
• Fix: Add workaround for snyk image scan failure by @sivanantha321 in #3880
• Fix trust_remote_code not working with huggingface backend by @sivanantha321 in #3879
• Update KServe 2024-2025 Roadmap by @yuzisun in #3810
• Configurable image pull secrets in Helm charts by @saileshd1402 in #3838
• Fix issue with rolling update behavior by @andyi2it in #3786
• Fix the 'tokens exceeding model limit' error response in vllm server by @saileshd1402 in #3886
• Add support for binary data extension protocol and FP16 datatype by @sivanantha321 in #3685
• Protobuf version upgrade 4.25.4 by @andyi2it in #3881
• Adds optional labels and annotations to the controller by @guitouni in #3366
• Enable Server-Side Apply for Kustomize Overlays in Test Environment by @Jooho in #3877
• bufix: update image_transformer.py to handle changes in input structure by @zwong91 in #3830
• support text embedding task in hugging face server by @kevinmingtarja in #3743
• Rename max_length parameter to max_model_len to be in sync with vLLM by @Datta0 in #3827
• [Upstream] - Update-istio version based on go version 1.21 by @mholder6 in #3825
• Enrich isvc NotReady events for failed conditions by @asdqwe123zxc in #3303
• adding metadata on requests by @gcemaj in #3635
• Publish 0.14.0-rc0 release by @yuzisun in #3867
• Use API token for publishing package to PyPI by @sivanantha321 in #3896
• Fix sdlc broken when kserve installed using helm by @sivanantha321 in #3890
• Add Security Context and Resources to RBAC Proxy by @HotsauceLee in #3898
• Remove unwanted cluster scope secret permissions by @sivanantha321 in #3893
• bump to vllm 0.5.5 by @lizzzcai in #3911
• pin gosec to 2.20.0 by @greenmoon55 in #3921
• add a new doc 'common issues and solutions' by @Jooho in #3878
• Implement health endpoint for vLLM backend by @sivanantha321 in #3850
• Add security best practices for inferenceservice, inferencegraph, servingruntimes by @sivanantha321 in #3917
• Bump Go to 1.22 by @sivanantha321 in #3912
• bump to vllm 0.6.0 by @hustxiayang in #3934
• Set the volume mount's readonly annotation based on the ISVC annotation by @hdefazio in #3885
• mount /dev/shm volume to huggingfaceserver by @lizzzcai in #3910
• Fix permission error in snyk scan by @sivanantha321 in #3889
• Cluster Local Model CR by @greenmoon55 in #3839
• added http headers to inbound request by @andyi2it in #3895
• Add prow-github-action by @sivanantha321 in #3888
• Add TLS support for Inference Loggers by @ruivieira in #3863
• Fix explainer endpoint not working with path based routing by @sivanantha321 in #3257
• Fix ingress configuration for path based routing and update go mod by @sivanantha321 in #3944
• Add HostIPC field to ServingRuntimePodSpec by @greenmoon55 in #3943
• remove conversion wehbook part from self-signed-ca.sh by @Jooho in #3941
• update fluid kserve sample to use huggingface servingruntime by @lizzzcai in #3907
• bump to vLLM0.6.1post2 by @hustxiayang in #3948
• Add NodeDownloadPending status to ClusterLocalModel by @greenmoon55 in #3955
• add tags to rest server timing logs to differentiate cpu and wall time by @gfkeith in #3954
• Implement Huggingface model download in storage initializer by @andyi2it in #3584
• Update OWNERS file by @yuzisun in #3966
• Cluster local model controller by @greenmoon55 in #3860
• Prepare for 0.14.0-rc1 release and automate sync process by @sivanantha321 in #3970
• add a new API for multi-node/multi-gpu by @Jooho in #3871
• Fix update-openapigen.sh that can be executed from kserve dir by @Jooho in #3924
• Add python 3.12 support and remove python 3.8 support by @sivanantha321 in #3645
• Fix openssl vulnerability CWE-1395 by @sivanantha321 in #3975
• Fix Kubernetes Doc Links by @jyono in #3670
• Fix kserve local testing env by @yuzisun in #3981
• Fix streaming response not working properly with logger by @sivanantha321 in #3847
• Add a flag for automount serviceaccount token by @greenmoon55 in https://github.com/kserve/ks...

v0.14.0-rc1

What's Changed

• Publish 0.14.0-rc0 release by @yuzisun in #3867
• Use API token for publishing package to PyPI by @sivanantha321 in #3896
• Fix sdlc broken when kserve installed using helm by @sivanantha321 in #3890
• Add Security Context and Resources to RBAC Proxy by @HotsauceLee in #3898
• Remove unwanted cluster scope secret permissions by @sivanantha321 in #3893
• bump to vllm 0.5.5 by @lizzzcai in #3911
• pin gosec to 2.20.0 by @greenmoon55 in #3921
• add a new doc 'common issues and solutions' by @Jooho in #3878
• Implement health endpoint for vLLM backend by @sivanantha321 in #3850
• Add security best practices for inferenceservice, inferencegraph, servingruntimes by @sivanantha321 in #3917
• Bump Go to 1.22 by @sivanantha321 in #3912
• bump to vllm 0.6.0 by @hustxiayang in #3934
• Set the volume mount's readonly annotation based on the ISVC annotation by @hdefazio in #3885
• mount /dev/shm volume to huggingfaceserver by @lizzzcai in #3910
• Fix permission error in snyk scan by @sivanantha321 in #3889
• Cluster Local Model CR by @greenmoon55 in #3839
• added http headers to inbound request by @andyi2it in #3895
• Add prow-github-action by @sivanantha321 in #3888
• Add TLS support for Inference Loggers by @ruivieira in #3863
• Fix explainer endpoint not working with path based routing by @sivanantha321 in #3257
• Fix ingress configuration for path based routing and update go mod by @sivanantha321 in #3944
• Add HostIPC field to ServingRuntimePodSpec by @greenmoon55 in #3943
• remove conversion wehbook part from self-signed-ca.sh by @Jooho in #3941
• update fluid kserve sample to use huggingface servingruntime by @lizzzcai in #3907
• bump to vLLM0.6.1post2 by @hustxiayang in #3948
• Add NodeDownloadPending status to ClusterLocalModel by @greenmoon55 in #3955
• add tags to rest server timing logs to differentiate cpu and wall time by @gfkeith in #3954
• Implement Huggingface model download in storage initializer by @andyi2it in #3584
• Update OWNERS file by @yuzisun in #3966
• Cluster local model controller by @greenmoon55 in #3860
• Prepare for 0.14.0-rc1 release and automate sync process by @sivanantha321 in #3970

New Contributors

• @HotsauceLee made their first contribution in #3898
• @hustxiayang made their first contribution in #3934
• @hdefazio made their first contribution in #3885
• @ruivieira made their first contribution in #3863
• @gfkeith made their first contribution in #3954

Full Changelog: v0.14.0-rc0...v0.14.0-rc1

v0.14.0-rc0

What's Changed

• Prevent the PassthroughCluster for clients/workloads in the service mesh by @israel-hdez in #3711
• Extract openai predict logic into smaller methods by @grandbora in #3716
• Bump MLServer to 1.5.0 by @sivanantha321 in #3740
• Refactor storage initializer to log model download time for all storage types by @sivanantha321 in #3735
• inferenceservice controller: fix error check in Serverless mode by @dtrifiro in #3753
• Add nccl package and Bump vLLM to 0.4.3 for huggingface runtime by @sivanantha321 in #3723
• Propagate trust_remote_code flag throughout vLLM startup by @calwoo in #3729
• Fix dead links on PyPI by @kevinbazira in #3754
• Fix model is ready even if there is no model by @HAO2167 in #3275
• Fix No model ready error in multi model serving by @sivanantha321 in #3758
• Initial implementation of Inference client by @sivanantha321 in #3401
• Fix logprobs for vLLM by @sivanantha321 in #3738
• Fix model name not properly parsed by inference graph by @sivanantha321 in #3746
• pillow - Buffer Overflow by @spolti in #3598
• Use add_generation_prompt while creating chat template by @Datta0 in #3775
• Deduplicate the names for the additional domain names by @houshengbo in #3773
• Make Virtual Service case-insensitive by @andyi2it in #3779
• Install packages needed for vllm model load by @gavrissh in #3802
• Make gRPC max message length configurable by @sivanantha321 in #3741
• Add readiness probe for MLServer and Increase memory for pmml in CI by @sivanantha321 in #3789
• Several bug fixes for vLLM completion endpoint by @sivanantha321 in #3788
• Increase timeout to make unit test stable by @Jooho in #3808
• Upgrade CI deps by @sivanantha321 in #3822
• Add tests for vLLM by @sivanantha321 in #3771
• Bump python to 3.11 for serving runtime images and Bump poetry to 1.8.3 by @sivanantha321 in #3812
• Bump vLLM to 0.5.3.post1 by @sivanantha321 in #3828
• Refactor the ModelServer to let uvicorn handle multiple workers and use 'spawn' for mutiprocessing by @sivanantha321 in #3757
• Update golang for docs/Dockerfile to 1.21 by @spolti in #3761
• Make ray an optional dependency by @sivanantha321 in #3834
• Update aif example by @spolti in #3765
• Use helm for quick installation by @sivanantha321 in #3813
• Allow KServe to have its own local gateways for Serverless mode by @israel-hdez in #3737
• Add support for Azure DNS zone endpoints by @tjandy98 in #3819
• Fix failed build for knativeLocalGatewayService by @yuzisun in #3866
• Add logging request feature for vLLM backend by @sivanantha321 in #3849
• Bump vLLM to 0.5.4 by @sivanantha321 in #3874
• Fix: Add workaround for snyk image scan failure by @sivanantha321 in #3880
• Fix trust_remote_code not working with huggingface backend by @sivanantha321 in #3879
• Update KServe 2024-2025 Roadmap by @yuzisun in #3810
• Configurable image pull secrets in Helm charts by @saileshd1402 in #3838
• Fix issue with rolling update behavior by @andyi2it in #3786
• Fix the 'tokens exceeding model limit' error response in vllm server by @saileshd1402 in #3886
• Add support for binary data extension protocol and FP16 datatype by @sivanantha321 in #3685
• Protobuf version upgrade 4.25.4 by @andyi2it in #3881
• Adds optional labels and annotations to the controller by @guitouni in #3366
• Enable Server-Side Apply for Kustomize Overlays in Test Environment by @Jooho in #3877
• bufix: update image_transformer.py to handle changes in input structure by @zwong91 in #3830
• support text embedding task in hugging face server by @kevinmingtarja in #3743
• Rename max_length parameter to max_model_len to be in sync with vLLM by @Datta0 in #3827
• [Upstream] - Update-istio version based on go version 1.21 by @mholder6 in #3825
• Enrich isvc NotReady events for failed conditions by @asdqwe123zxc in #3303
• adding metadata on requests by @gcemaj in #3635

New Contributors

• @calwoo made their first contribution in #3729
• @guitouni made their first contribution in #3366
• @zwong91 made their first contribution in #3830
• @mholder6 made their first contribution in #3825
• @asdqwe123zxc made their first contribution in #3303
• @gcemaj made their first contribution in #3635

Full Changelog: v0.13.0...v0.14.0-rc0

v0.13.1

What's Changed

• Add nccl package and Bump vLLM to 0.4.3 for huggingface runtime by @sivanantha321 (#3723)
• Propagate trust_remote_code flag throughout vLLM startup by @calwoo (#3729)
• Use add_generation_prompt while creating chat template by @Datta0 (#3775)
• Fix logprobs for vLLM by @sivanantha321 (#3738)
• Install packages needed for vllm model load by @gavrissh (#3802)
• Publish 0.13.1 Release by @johnugeorge in #3824

Full Changelog: v0.13.0...v0.13.1

v0.13.0

🌈 What's New?

• add support for async streaming in predict by @alexagriffith in #3475
• Fix: Support model parallelism in HF transformer by @gavrishp in #3459
• Support model revision and tokenizer revision in huggingface server by @lizzzcai in #3558
• OpenAI schema by @tessapham in #3477
• Support OpenAIModel in ModelRepository by @grandbora in #3590
• updated xgboost to support json and ubj models by @andyi2it in #3551
• Add OpenAI API support to Huggingfaceserver by @cmaddalozzo in #3582
• VLLM support for OpenAI Completions in HF server by @gavrishp in #3589
• Add a user friendly error message for http exceptions by @grandbora in #3581
• feat: Provide minimal distribution of CRDs by @terrytangyuan in #3492
• set default SAFETENSORS_FAST_GPU and HF_HUB_DISABLE_TELEMETRY in HF Server by @lizzzcai in #3594
• Enabled the multiple domains support on an inference service by @houshengbo in #3615
• Add base model for proxying request to an OpenAI API enabled model server by @cmaddalozzo in #3621
• Add headers to predictor exception logging by @grandbora in #3658
• Enhance controller setup based on available CRDs by @israel-hdez in #3472
• Add openai models endpoint by @cmaddalozzo in #3666
• feat: Support customizable deployment strategy for RawDeployment mode. Fixes #3452 by @terrytangyuan in #3603
• Enable dtype support for huggingface server by @Datta0 in #3613
• Add method for checking model health/readiness by @cmaddalozzo in #3673
• Unify the log configuration using kserve logger by @sivanantha321 in #3577
• Add the field ResponseStartTimeoutSeconds to create ksvc by @houshengbo in #3705
• Add FP16 datatype support for OIP grpc by @sivanantha321 in #3695
• Add option for returning probabilities in huggingface server by @andyi2it in #3607

⚠️ What's Changed

• Remove conversion webhook from manifests by @Jooho in #3476
• Remove cluster level list/watch for configmaps, serviceaccounts, secrets by @sivanantha321 in #3469
• chore: Remove Seldon Alibi dependencies. Fixes #3380 by @terrytangyuan in #3443
• docs: Move Alibi explainer to docs by @terrytangyuan in #3579
• Remove generate endpoints by @cmaddalozzo in #3654
• Remove conversion webhook from kubeflow manifest patch by @sivanantha321 in #3700

🐛 What's Fixed

• Fix:Support Parallelism in vllm runtime by @gavrishp in #3464
• fix: Instantiate HuggingfaceModelRepository only when model cannot be loaded. Fixes #3423 by @terrytangyuan in #3424
• Fix isADirectoryError in Azure blob download by @tjandy98 in #3502
• Fix bug: Remove redundant helm chart affinity on predictor CRD by @trojaond in #3481
• Make the modelcar injection idempotent by @rhuss in #3517
• Only pad left for decode-only architecture models. by @sivanantha321 in #3534
• fix lint typo on Makefile by @spolti in #3569
• fix: Set writable cache folder to avoid permission issue. Fixes #3562 by @terrytangyuan in #3576
• Fix model unload in server stop method by @sivanantha321 in #3587
• Fix golint errors by @andyi2it in #3552
• Fix make deploy-dev-storage-initializer not working by @sivanantha321 in #3617
• Fix Pydantic 2 warnings by @cmaddalozzo in #3622
• build: Fix CRD copying in generate-install.sh by @terrytangyuan in #3620
• Only load from model repository if model binary is not found under model_dir by @sivanantha321 in #3559
• build: Remove misleading logs from minimal-crdgen.sh by @terrytangyuan in #3641
• Assign device to input tensors in huggingface server with huggingface backend by @saileshd1402 in #3657
• Fix Huggingface server stopping criteria by @cmaddalozzo in #3659
• Explicitly specify pad token id when generating tokens by @sivanantha321 in #3565
• Fix quick install does not cleans up Istio installer by @sivanantha321 in #3660
• fix for extract zip from gcs by @andyi2it in #3510
• fix: HPA equality check should include annotations by @terrytangyuan in #3650
• Fix: model id and model dir check order by @yuzisun in #3680
• Fix:vLLM Model Supported check throwing circular dependency by @gavrishp in #3688
• Fix: Allow null in Finish reason streaming response in vLLM by @gavrishp in #3684
• Fix kserve version is not updated properly by python-release.sh by @sivanantha321 in #3707
• Add precaution again running v1 endpoints on openai models by @grandbora in #3694
• Typos and minor fixes by @alpe in #3429
• Fix model_id and model_dir precedence for vLLM by @yuzisun in #3718
• Fixup max_length for HF and model info for vLLM by @Datta0 in #3715
• Fix prompt token count and provide completion usage in OpenAI response by @sivanantha321 in #3712

⬆️ Version Upgrade

• Upgrade orjson to version 3.9.15 by @spolti in #3488
• feat: upgrade to new fastapi, update models to handle both pydantic v… by @timothyjlaurent in #3374
• Update cert manager version in quick install script by @shauryagoel in #3496
• ci: Bump minikube version to work with newer K8s version by @terrytangyuan in #3498
• upgrade knative to 1.13 by @andyi2it in #3457
• Upgrade istio to 1.20 works for the Github Actions by @houshengbo in #3529
• chore: Bump ModelMesh version to v0.12.0-rc0 in Helm chart by @terrytangyuan in #3642
• upgrade vllm/transformers version by @johnugeorge in #3671

🔨 Project SDLC

• Enhance CI environment by @sivanantha321 in #3440
• Fixed go lint error using golangci-lint tool. by @andyi2it in #3378
• chore: Update list of reviewers by @ckadner in #3484
• build: Add helm docs update to make generate command by @terrytangyuan in #3437
• Added v2 infer test for supported model frameworks. by @andyi2it in #3349
• fix the quote format same with others and docstrings by @leyao-daily in #3490
• remove unnecessary Istio settings from quick_install.sh by @peterj in #3493
• Remove GOARCH by @mkumatag in #3523
• GH Alert: Potential file inclusion via variable by @spolti in #3520
• Update codeQL to v3 by @spolti in #3548
• switch e2e test inference graph to raw mode by @andyi2it in #3511
• Black lint by @cmaddalozzo in #3568
• Fix python linter by @sivanantha321 in #3571
• build: Add flake8 and black to pre-commit hooks by @terrytangyuan in #3578
• build: Allow pre-commit to keep changes in reformatted code by @terrytangyuan in #3604
• Allow rerunning failed workflows by comment by @andyi2it in #3550
• add re-run info in the PR templates by @spolti in #3633
• Add e2e tests for huggingface by @sivanantha321 in #3600
• Test image builds for ARM64 arch in CI by @sivanantha321 in #3629
• workflow file for cherry-pick on comment by @andyi2it in #3653
• Fix: huggingface runtime in helm chart by @yuzisun in #3679
• Copy generated CRDs by kustomize to Helm by @Jooho in #3392
  ...

v0.13.0-rc1

What's Changed

• upgrade vllm/transformers version by @johnugeorge in #3671
• Add openai models endpoint by @cmaddalozzo in #3666
• feat: Support customizable deployment strategy for RawDeployment mode. Fixes #3452 by @terrytangyuan in #3603
• Enable dtype support for huggingface server by @Datta0 in #3613
• Add method for checking model health/readiness by @cmaddalozzo in #3673
• fix for extract zip from gcs by @andyi2it in #3510
• Update Dockerfile and Readme by @gavrishp in #3676
• Update huggingface readme by @alexagriffith in #3678
• fix: HPA equality check should include annotations by @terrytangyuan in #3650
• Fix: huggingface runtime in helm chart by @yuzisun in #3679
• Fix: model id and model dir check order by @yuzisun in #3680
• Fix:vLLM Model Supported check throwing circular dependency by @gavrishp in #3688
• Fix: Allow null in Finish reason streaming response in vLLM by @gavrishp in #3684
• Unify the log configuration using kserve logger by @sivanantha321 in #3577
• Remove conversion webhook from kubeflow manifest patch by @sivanantha321 in #3700
• Add the field ResponseStartTimeoutSeconds to create ksvc by @houshengbo in #3705

New Contributors

• @Datta0 made their first contribution in #3613

Full Changelog: v0.13.0-rc0...v0.13.0-rc1

v0.13.0-rc0

🌈 What's New?

• add support for async streaming in predict by @alexagriffith in #3475
• Fix: Support model parallelism in HF transformer by @gavrishp in #3459
• Support model revision and tokenizer revision in huggingface server by @lizzzcai in #3558
• OpenAI schema by @tessapham in #3477
• Support OpenAIModel in ModelRepository by @grandbora in #3590
• updated xgboost to support json and ubj models by @andyi2it in #3551
• Add OpenAI API support to Huggingfaceserver by @cmaddalozzo in #3582
• VLLM support for OpenAI Completions in HF server by @gavrishp in #3589
• Add a user friendly error message for http exceptions by @grandbora in #3581
• feat: Provide minimal distribution of CRDs by @terrytangyuan in #3492
• set default SAFETENSORS_FAST_GPU and HF_HUB_DISABLE_TELEMETRY in HF Server by @lizzzcai in #3594
• Enabled the multiple domains support on an inference service by @houshengbo in #3615
• Add base model for proxying request to an OpenAI API enabled model server by @cmaddalozzo in #3621
• Add headers to predictor exception logging by @grandbora in #3658
• Enhance controller setup based on available CRDs by @israel-hdez in #3472

⚠️ What's Changed

• Remove conversion webhook from manifests by @Jooho in #3476
• Remove cluster level list/watch for configmaps, serviceaccounts, secrets by @sivanantha321 in #3469
• chore: Remove Seldon Alibi dependencies. Fixes #3380 by @terrytangyuan in #3443
• docs: Move Alibi explainer to docs by @terrytangyuan in #3579
• Remove generate endpoints by @cmaddalozzo in #3654

🐛 What's Fixed

• Fix:Support Parallelism in vllm runtime by @gavrishp in #3464
• fix: Instantiate HuggingfaceModelRepository only when model cannot be loaded. Fixes #3423 by @terrytangyuan in #3424
• Fix isADirectoryError in Azure blob download by @tjandy98 in #3502
• Fix bug: Remove redundant helm chart affinity on predictor CRD by @trojaond in #3481
• Make the modelcar injection idempotent by @rhuss in #3517
• Only pad left for decode-only architecture models. by @sivanantha321 in #3534
• fix lint typo on Makefile by @spolti in #3569
• fix: Set writable cache folder to avoid permission issue. Fixes #3562 by @terrytangyuan in #3576
• Fix model unload in server stop method by @sivanantha321 in #3587
• Fix golint errors by @andyi2it in #3552
• Fix make deploy-dev-storage-initializer not working by @sivanantha321 in #3617
• Fix Pydantic 2 warnings by @cmaddalozzo in #3622
• build: Fix CRD copying in generate-install.sh by @terrytangyuan in #3620
• Only load from model repository if model binary is not found under model_dir by @sivanantha321 in #3559
• build: Remove misleading logs from minimal-crdgen.sh by @terrytangyuan in #3641
• Assign device to input tensors in huggingface server with huggingface backend by @saileshd1402 in #3657
• Fix Huggingface server stopping criteria by @cmaddalozzo in #3659
• Explicitly specify pad token id when generating tokens by @sivanantha321 in #3565
• Fix quick install does not cleans up Istio installer by @sivanantha321 in #3660

⬆️ Version Upgrade

• Upgrade orjson to version 3.9.15 by @spolti in #3488
• feat: upgrade to new fastapi, update models to handle both pydantic v… by @timothyjlaurent in #3374
• Update cert manager version in quick install script by @shauryagoel in #3496
• ci: Bump minikube version to work with newer K8s version by @terrytangyuan in #3498
• upgrade knative to 1.13 by @andyi2it in #3457
• Upgrade istio to 1.20 works for the Github Actions by @houshengbo in #3529
• chore: Bump ModelMesh version to v0.12.0-rc0 in Helm chart by @terrytangyuan in #3642

🔨 Project SDLC

• Enhance CI environment by @sivanantha321 in #3440
• Fixed go lint error using golangci-lint tool. by @andyi2it in #3378
• chore: Update list of reviewers by @ckadner in #3484
• build: Add helm docs update to make generate command by @terrytangyuan in #3437
• Added v2 infer test for supported model frameworks. by @andyi2it in #3349
• fix the quote format same with others and docstrings by @leyao-daily in #3490
• remove unnecessary Istio settings from quick_install.sh by @peterj in #3493
• Remove GOARCH by @mkumatag in #3523
• GH Alert: Potential file inclusion via variable by @spolti in #3520
• Update codeQL to v3 by @spolti in #3548
• switch e2e test inference graph to raw mode by @andyi2it in #3511
• Black lint by @cmaddalozzo in #3568
• Fix python linter by @sivanantha321 in #3571
• build: Add flake8 and black to pre-commit hooks by @terrytangyuan in #3578
• build: Allow pre-commit to keep changes in reformatted code by @terrytangyuan in #3604
• Allow rerunning failed workflows by comment by @andyi2it in #3550
• add re-run info in the PR templates by @spolti in #3633
• Add e2e tests for huggingface by @sivanantha321 in #3600
• Test image builds for ARM64 arch in CI by @sivanantha321 in #3629
• workflow file for cherry-pick on comment by @andyi2it in #3653

CVE patches

• CVE-2024-24762 - update fastapi to 0.109.1 by @spolti in #3556
• golang.org/x/net Allocation of Resources Without Limits or Throttling by @spolti in #3596
• Fix CVE-2023-45288 for qpext by @sivanantha321 in #3618
• Security fix - CVE 2024 24786 by @andyi2it in #3585

📝 Documentation Update

• qpext: fix a typo in qpext doc by @daixiang0 in #3491
• Update KServe project description by @yuzisun in #3524
• Update kserve cake diagram by @yuzisun in #3530
• Remove white background for the kserve diagram by @yuzisun in #3531
• fix a typo in OPENSHIFT_GUIDE.md by @marek-veber in #3544
• Fix typo in README.md by @terrytangyuan in #3575

New Contributors

• @leyao-daily made their first contribution in #3490
• @peterj made their first contribution in #3493
• @timothyjlaurent made their first contribution in #3374
• @shauryagoel made their first contribution in #3496
• @mkumatag made their first contribution in #3523
• @marek-veber made their first contribution in #3544
• @trojaond made their first contribution in #3481
• @grandbora made their first contribution in #3590
• @saileshd1402 made their first contribution in #3657

Full Changelog: v0.12.1...v0.13.0-rc0

v0.12.1

What's Changed

• [release-0.12] Update fastapi to 0.109.1 and Support ray 2.10 by @sivanantha321 in #3609
• [release-0.12] Pydantic 2 support by @cmaddalozzo in #3614
• [release-0.12] Make the modelcar injection idempotent by @sivanantha321 in #3612
• Prepare for release 0.12.1 by @sivanantha321 in #3610
• release-0.12 pin back ray to 2.10 by @yuzisun in #3616
• [release-0.12] Fix docker build failure for ARM64 by @sivanantha321 in #3627

Full Changelog: v0.12.0...v0.12.1

v0.12.0

🌈 What's New?

Core Inference & Serving Runtimes

• Implement HuggingFace model server by @yuzisun in #3334
• feat: Add HuggingFace runtime out-of-the-box support by @terrytangyuan in #3395
• Implement support for vllm as alternative backend by @gavrishp in #3415
• Torchserve grpc v2 by @andyi2it in #3247
• feat: CA bundle mount options for storage initializer by @Jooho in #3250
• Add support for modelcars by @rhuss in #3110
• Add compatibility for Istio CNI plugin by @israel-hdez in #3316
• feat: Allow to disable ingress creation for raw deployment mode by @terrytangyuan in #3436

Advanced Inference

• RawDeployment support for Inference Graph by @bmopuri in #3199, @bmopuri in #3194
• Added custom request timeout for inferencegraph. by @andyi2it in #3173
• Add regex support for propagating IG headers by @sivanantha321 in #3178

KServe Python SDK, Storage

• Unpack archive files for hdfs by @sivanantha321 in #3093
• feat: Support S3 transfer acceleration by @terrytangyuan in #3305

⚠️ What's Changed

• Change the default value for enableDirectPvcVolumeMount to true by @Jooho in #3371
• Add model arguments to API and update BERT inference example by @yuzisun in #3332

--model_name, --predictor_host, --predictor_use_ssl, --predictor_request_timeout_seconds are added to the kserve model server and no longer need to be defined in the custom predictor or transformer. --protocol is deprecated and superceded by --predictor_protocol. More details can be found on API reference doc.

🐛 What's Fixed

• Removing update op from pod-mutator webhook by @rachitchauhan43 in #3163
• Fix quick install script by @dtrifiro in #3164
• Fix self-signed-ca installation by @sivanantha321 in #3165
• Add S3_VERIFY_SSL to storage.py for S3 by @Jooho in #3172
• Fix runtime not found for triton due to wrong default protocolVersion by @sivanantha321 in #3177
• Make ModelServer to stop correctly when using more than 1 worker by @andyi2it in #3174
• Fix serving runtime webhook cert namespace for kubeflow installation by @sivanantha321 in #3188
• Fix knative config-defaults values overrided by kserve by @sivanantha321 in #3130
• Fix qpext metrics port by @yuzisun in #3209
• Added async with postprocess method. by @andyi2it in #3204
• Fix lightgbm model input conversion when input is list of lists by @sivanantha321 in #3226
• Validation added for ensuring same model format has same priority for runtime by @andyi2it in #3181
• Fix: Unexpected Panic in Inference graph when it fails to create http request by @HAO2167 in #3079
• Support verify variable with storage-config json style (fix-3263) by @Jooho in #3267
• s3 storage initializer: only set environment variables if variables are set in storage secret json by @dtrifiro in #3259
• Fix tensorflow e2e test fails due to OOM error by @sivanantha321 in #3293
• fix: Properly handle the creation and closure of success file in DownloadModel() by @terrytangyuan in #3295
• fix: Surface errors when writing graphHandler response by @terrytangyuan in #3308
• Fix qpext hangs during shutdown by @sivanantha321 in #3268
• fix: Check if HPA has the same scaleTargetRef and behavior by @terrytangyuan in #3294
• Updated quick_install script to temporarily fix 0.11.2 release install by @andyi2it in #3311
• image_patch_dev.sh: set pipefail by @dtrifiro in #3274
• Move pmml worker validation to runtime by @sivanantha321 in #3182
• Introduce retry on resource conflict by @sivanantha321 in #3240
• Fix inference request fails when sending with less number of features than the total model features on lightgbm by @sivanantha321 in #3313
• Fix raw deployment service points to predictor container port instead of transformer container port in transformer collocation by @sivanantha321 in #3318
• Restrict storage uri to predictor only in collocation of transformer and predictor by @sivanantha321 in #3280
• feat: Expose defaults for several batcher handler parameters by @terrytangyuan in #3301
• fix: Properly close resources and handle errors in agent and storage. Fixes #3323 by @terrytangyuan in #3321
• Handles s3 download for object name starts with folder name. by @andyi2it in #3205
• chore: Remove unused timeout annotation and flag in batcher by @terrytangyuan in #3341
• Pass missing infer parameters during conversion by @sivanantha321 in #3368
• Add exception handler for model server and Add ability to specify custom handler by @sivanantha321 in #3405
• fix: Add missing volume mount to transformer container when using modelcars by @rhuss in #3384
• fix: Add 'model_version' to InferResponse in python library by @ajstewart in #3466
• Fix v2 model ready url in kserve client by @sivanantha321 in #3403
• Fix parameters value type conversion by pydantic by @sivanantha321 in #3430
• Fix Raw Logger E2E by @israel-hdez in #3434
• Expose qpext aggregate metrics port on container by @sivanantha321 in #3291
• Fix dup metrics aggr port by @yuzisun in #3447
• fix: HuggingFace predictor should not be recognized as multi-model server by @terrytangyuan in #3449
• Fix: bugs for huggingface runtime template by @yuzisun in #3448
• Fix: Add padding and truncation in huggingface tokenizer by @kevinmingtarja in #3450
• Fix: vllm backend does not work with model_dir for huggingface runtime by @yuzisun in #3456
• Fix azure workload identity federation by excluding azure client secret by @robbertvdg in #3390
• Change certificate to ca_bundle in json style of s3 storageSecret by @Jooho in #3463

⬆️ Version Upgrade

• Upgrade istio Api and migrate to v1beta1 Api version by @sivanantha321 in #3150
• Bump torchserve version to 0.9.0 by @gavrishp in #3217
• Allow ray >=2.7,<3 by @ddelange in #3075
• Bump istio version to 1.19.4 by @sivanantha321 in #3258
• Updated ray to 2.8.0 and removed detached flag to avoid deprecation error in future by @andyi2it in #3272
• chore: Upgrade to XGBoost v2.0.2. Fixes #3310 by @terrytangyuan in #3309
• chore: Upgrade Go to v1.21 by @terrytangyuan in #3296
• Added 3.11 support for paddle in workflow. by @andyi2it in #3246
• Upgraded poetry version to 1.7.1 by @andyi2it in #3271
• Upgrade cloudevent to v2 by @homily707 in #3255
• Update knative-serving by @spolti in #3362
• Update google-cloud-storage dependecy to >=2.3.0,<3.0.0 and ray dependency to >=2.8.1, <3.0.0 by @sivanantha321 in #3389

🔨 Project SDLC

• chore: Add design doc template links to feature request template by @ckadner in #3155
• Make storage initializer image configurable by @yuzisun in #3145
• Increase pytest workers for kourier e2e test by @sivanantha321 in #3151
• Restrict workflow concurrency by @vignesh-murugani2i in #3167
• Generate client-go for StorageContainer CR by @sivanantha321 in #3152
• Refractor v1 vs. v2 endpoint unit tests in kserve/test/test_server.py… by @guohaoyu110 in #3158
• Verify codegen in CI by @sivanantha321 in...

v0.12.0-rc1

What's Changed

• docs: Corrections and edits on release process document by @terrytangyuan in #3326
• build: Switch to use kustomize in kubectl to simplify build process. Fixes #3314 by @terrytangyuan in #3315
• feat: Expose defaults for several batcher handler parameters by @terrytangyuan in #3301
• fix: Properly close resources and handle errors in agent and storage. Fixes #3323 by @terrytangyuan in #3321
• Add model arguments to API and update BERT inference example by @yuzisun in #3332
• chore: Update generated APIs and check generated manifests by @terrytangyuan in #3335
• Update python model serving runtime API docstring by @yuzisun in #3338
• Handles s3 download for object name starts with folder name. by @andyi2it in #3205
• chore: Remove unused timeout annotation and flag in batcher by @terrytangyuan in #3341
• ci: Automate release process by @terrytangyuan in #3345
• fixes critical vulnerabilities on ray by @spolti in #3285
• chore: Bump versions to prepare v0.12.0-rc1 release by @terrytangyuan in #3352
• Change version for helm charts in README by @gawsoftpl in #3353
• Fixes CVE-2023-48795 by @spolti in #3354
• Fix Stack-based Buffer Overflow on protobuf by @spolti in #3358
• Update knative-serving by @spolti in #3362
• Fixes vulnerabilities on the otelhttp dependency by @spolti in #3361
• Change the default value for enableDirectPvcVolumeMount to true by @Jooho in #3371
• feat: Automatically generate Helm Chart docs. Fixes #3356 by @terrytangyuan in #3363
• Modified script for include all kserve poetry projects. by @andyi2it in #3350
• RawDeployment support for Inference Graph by @bmopuri in #3199
• Add compatibility for Istio CNI plugin by @israel-hdez in #3316
• Pass missing infer parameters during conversion by @sivanantha321 in #3368
• feat: Support S3 transfer acceleration by @terrytangyuan in #3305
• Implement HuggingFace model server by @yuzisun in #3334
• fix: Add missing volume mount to transformer container when using modelcars by @rhuss in #3384
• align cloudevents/sdk-go dependency by @spolti in #3387

New Contributors

• @gawsoftpl made their first contribution in #3353

Full Changelog: v0.12.0-rc0...v0.12.0-rc1