OME 0.1.4

📦 Container Images

The following container images are available:

# OME Manager
docker pull ghcr.io/moirai-internal/ome-manager:v0.1.4

# Model Agent
docker pull ghcr.io/moirai-internal/model-agent:v0.1.4

# OME Agent
docker pull ghcr.io/moirai-internal/ome-agent:v0.1.4

# Multinode Prober
docker pull ghcr.io/moirai-internal/multinode-prober:v0.1.4

⎈ Helm Installation

Option 1: OCI Registry (Recommended)

# Install directly from OCI registry
helm install ome-crd oci://ghcr.io/moirai-internal/charts/ome-crd --version 0.1.4 --namespace ome --create-namespace
helm install ome oci://ghcr.io/moirai-internal/charts/ome-resources --version 0.1.4 --namespace ome

Option 2: GitHub Releases

# Add the OME Helm repository
helm repo add ome https://github.com/sgl-project/ome/releases/download/v0.1.4
helm repo update

# Install OME
helm install ome-crd ome/ome-crd --namespace ome --create-namespace
helm install ome ome/ome-resources --namespace ome

📋 Changelog

📄 Software Bill of Materials

SBOMs are available in both SPDX and CycloneDX formats for:

• Source code
• All container images

🔐 Signatures

All container images are signed with cosign. Verify with:

cosign verify ghcr.io/moirai-internal/ome-manager:v0.1.4   --certificate-identity-regexp=https://github.com/sgl-project/ome/.github/workflows/release.yaml@refs/tags/.*   --certificate-oidc-issuer=https://token.actions.githubusercontent.com

What's Changed

• [misc] cleanup docs by @slin1237 in #197
• fix: benchmark container volume mounts update when base model exists by @carlory in #198
• style: 🔨 optimize import order and more readable. by @yafengio in #191
• [misc] update kimi k2 runtime by @slin1237 in #200
• [misc] update default kimi isvc with ingres disabled by @slin1237 in #201
• [misc] update kimi k2 runtime to remove volumes and env by @slin1237 in #202
• [WIP] Update kimi-k2-pd-rt.yaml by @Atream in #203
• Fix error message for invalid deployment mode by @carlory in #207
• [Bugfix]: verify KEDA ScaledObject CRD is registered before deletion by @bindrad in #206
• [Docs] Fix serving_runtime doc by @bcfre in #218
• Bump cross-env from 7.0.3 to 10.0.0 in /site by @dependabot[bot] in #219
• chart: support for user-defined model agent tolerations by @my-git9 in #221
• [Docs] Improve readability and logical flow of installation guide by @JiangJiaWei1103 in #224
• [Bugfix] Wait for the OME controller Pod to become ready by @JiangJiaWei1103 in #228
• [misc] fix github page version by @slin1237 in #232
• [Misc] Add PVC support to OME agent replica by @beiguo218 in #229
• add acceleratorClass crd by @pallasathena92 in #215
• [misc] upgrade lws version to latest by @slin1237 in #231
• [misc] add oss gpt models by @slin1237 in #233
• [misc] add oss gpt bf16 models by @slin1237 in #234
• [misc] add ut for oss 120b models by @slin1237 in #235
• [BUG]Fix BenchmarkJob Deprecated Storage Command by @YouNeedCryDear in #239
• [Bug]fix openai api violation for accelerator crd by @pallasathena92 in #242
• [BUG]Fix api-backend default value for benchmark job by @YouNeedCryDear in #241
• [Misc] Add checksum upload support in ome agent replica when using OCI as target by @beiguo218 in #240
• Bump actions/download-artifact from 4 to 5 by @dependabot[bot] in #237
• [oep] add proposal for accelerator aware runtime selection by @slin1237 in #129
• Extend ServingRuntime API for Accelerator Support by @pallasathena92 in #246
• [Core] Add local filesystem storage support for model weights by @slin1237 in #253
• feat: support set global hub for chart images by @my-git9 in #251
• add runtime-type helper function test by @pallasathena92 in #249
• [bugfix] add back omitempty on spec and status by @slin1237 in #254
• [bugfix] fix accelerator class Quantity spec by @slin1237 in #256
• [docs] Update Bootstrap utility classes following Bootstrap 5 breaking changes by @yankay in #255
• [bugfix] patch deepseek runtime by @slin1237 in #259
• Support extra volumes and mounts in model-agent by @abatilo in #260
• Extend inferenceService API for Accelerator Support by @pallasathena92 in #258
• [misc] improve hf hub module by @slin1237 in #261
• [core] implement storage interface for multi cloud support by @slin1237 in #262
• [core] implement oci storage by @slin1237 in #263
• [core] implement s3 storage base structure by @slin1237 in #264
• [misc] storage bug fixes and code clean up by @slin1237 in #265
• [core] add s3 and minio storage provider and download option support by @slin1237 in #266
• [core] gcp storage provider base structure by @slin1237 in #267
• Bump actions/setup-go from 5 to 6 by @dependabot[bot] in #272
• Bump actions/setup-node from 4 to 5 by @dependabot[bot] in #271
• Bump actions/github-script from 7 to 8 by @dependabot[bot] in #270
• [Task5]accelerator class controller by @pallasathena92 in #276
• Bump actions/checkout from 4 to 5 by @dependabot[bot] in #245
• [Misc] Add XET-Core Rust Integration for HuggingFace Hub Downloads by @beiguo218 in #277
• [Misc] Add Dockerfile for XET Rust binding linux build by @beiguo218 in #278
• [Misc] Add XET-Core Go binding for HuggingFace Hub Downloads by @pallasathena92 in #279
• [Docs] Add READMEs for Xet binding by @beiguo218 in #280
• [Misc]add static library .a in gitignore by @pallasathena92 in #281
• [core] add pdb controller in ome by @pallasathena92 in #283
• [Misc] Updates in model agent for model deletion: avoid model path deletion when it is referred by other models by @beiguo218 in #284
• [Misc] Migrate to use XET-Core Rust based HF Hub in ome-agent replica by @beiguo218 in #282
• [Core]add runtime selector logic with Awareness AcceleratorClasses by @pallasathena92 in #285
• [Bugfix] Fix list_files fn in XET-Core Rust Hub implementation - implement recursive file listing by @beiguo218 in #286
• Bump cross-env from 10.0.0 to 10.1.0 in /site by @dependabot[bot] in #287
• [Core]Integrate the accelerator‑aware runtime into the InferenceService con… by @pallasathena92 in #289
• [Docs]update code owner by @pallasathena92 in #291
• Bump github/codeql-action from 3 to 4 by @dependabot[bot] in #292
• [OEP]OEP-0005: Model Context Protocol (MCP) Support Design by @YouNeedCryDear in #290
• [Core]Integrate the accelerator‑aware runtime into the InferenceServi… by @pallasathena92 in #293
• [API][Misc] Add new model capabilities and update its determination logic by @beiguo218 in #294
• [Misc] Add more OCI instance types in instance_type_util by @beiguo218 in #295
• [Misc] Add model config parsing support for more model types by @beiguo218 in #296
• [Docs] add readme for AC and update readme for runtime selector by @pallasathena92 in #297
• [Misc][Helm] Add retry logic to scout cache sync by @beiguo218 in #299
• Bump actions/setup-node from 5 to 6 by @dependabot[bot] in #298
• [Helm]add rbac for pdb by @pallasathena92 in #300
• [Bugfix]fix runnerspec during migration by @pallasathena92 in #301
• [Bugfix]fix runnerspec during migration unit test by @pallasathena92 in #302
• Bump actions/download-artifact from 5 to 6 by @dependabot[bot] in #305
• Bump actions/upload-artifact from 4 to 5 by @dependabot[bot] in #304
• [Core] modify old predictor deployment cleanup logic by @pallasathena92 in #303
• [Misc] Support qwen3_vl model for config parsing; Improve qwen3 vision model parameter estimation logic by @beiguo218 in #307
• Add instance type for Nebius by @Kangyan-Zhou in #309
• [Bugfix] Download Model with Xet HF Hub Client by @XinyueZhang369 in #313
• Make OME Deployment Flexible with GPU only option; Improve Build Cache and Docker Build by @Kangyan-Zhou in #310
• Bump autoprefixer from 10.4.21 to 10.4.22 in /site by @dependabot[bot] in #315
• unify retry logic in basemodel controller and update Kong docs link by @ErikJiang in #316
• [Misc] update error handle during processbaseLable by @pallasathena92 in #318
• [Misc] refactor router status update using util function by @pallasathena92 in #320
• Validate ClusterServingRuntime and ServingRuntime resources only reference known accelerator classes by @Kangyan-Zhou in #317
• [Bugfix] fix MergeNodeSelector with different componentType by @pallasathena92 in #322
• Bump actions/checkout from 5 to 6 by @dependabot[bot] in #321
• [Misc]revert ome-agent dockerfile by @pallasathena92 in #323

New Contributors

• @Atream made their first contribution in #203
• @bindrad made their first contribution in #206
• @bcfre made their first contribution in #218
• @my-git9 made their first contribution in #221
• @JiangJiaWei1103 made their first contribution in #224
• @yankay made their first contribution in #255
• @Kangyan-Zhou made their first contribution in #309
• @XinyueZhang369 made their first contribution in #313
• @ErikJiang made their first contribution in #316

Full Changelog: v0.1.3...v0.1.4