Releases: oracle-quickstart/oci-ai-blueprints
OCI AI Blueprints v1.0.7
Release Change Audit Report
New Version: v1.0.7
Previous Version: v1.0.5
Generated: 2025-08-07 14:56:56
Repositories Analyzed:
- Quickstarts Repo (
oci-ai-blueprints
) - Control Plane Repo (
corrino
) - Portal Repo (
oci_ai_blueprints_portal
)
Version v1.0.7 — Release Notes (Upgrade from v1.0.5)
Release Date: 2025-08-07
1. Executive Summary
v1.0.7 expands GPU-inference capabilities, hardens the secrets workflow, and streamlines API & UX touch-points across the stack.
Key highlights:
- AMD MI300x support end-to-end (Quickstarts blueprints & exporters, Control Plane node-pool provisioning, Portal library entries)
- Inference Benchmarking blueprints for offline (vLLM, LLMPerf) and online runs with MLflow logging
- Secrets Management v2 — namespaced Secrets API plus turnkey examples for opaque, registry, Hugging Face, and NVIDIA NIM credentials
- Blueprint Library evolution — new categories with richer filtering
- Auto-generated OpenAPI spec via DRF-Spectacular for easier client generation
- Portal UI overhaul for faster blueprint discovery and clearer deployment status
2. Repository-Specific Changes
Quickstarts Repo (v1.0.7)
New Features
- AMD MI300x
- Metrics exporter & plugin
llama4_maverick_amd.json
sample blueprint- MI300x specs added to RDMA tables
- Inference Benchmarking
- Offline (vLLM, LLMPerf) & online GPU benchmarks
- Sample configs, MLflow integration, dedicated READMEs
- Secrets Integration
- Examples covering opaque, registry, Hugging Face, and NIM secrets
- Partner Blueprints
- First entry: Llama Stack (partner_blueprints category)
Improvements
- Parameter rename:
local_directory_path
→node_directory_path
- Expanded JSON schema (
gpu_benchmarking
,model_serving
,partner_blueprints
) - Clearer offline-inference Object Storage mounting docs & IAM policy guidance
Technical Changes
- Terraform/Helm modules updated for AMD exporter & MI300x node pools
docs/sample_blueprints
re-organized in quickstart
Bug Fixes & Documentation
- Purged outdated inference configs
- READMEs enriched (benchmarking, secrets, version matrix)
Control Plane Repo (v1.0.7)
New Features
- MI300x hardware detection & recipe deployment
- Local filesystem volumes (input/output)
- Subnet-ID syntax validator
- DRF-Spectacular integration (auto-gen
schema.yml
) - Secrets API adds
namespace
field with richer examples
Improvements
- Simplified Swagger routing
- Extended JSON schema with Partner category & new classifications
- Clearer documentation around the deployment API control plane endpoint (examples & error messaging)
Bug Fixes
- Fixed OpenAPI schema generation tests
- Resolved DRF-Spectacular validation edge cases
Technical Changes
- Re-structured
api/models/*
; removedutils/models.py
- Added
drf-spectacular
dependency; legacy docs removed - New
README.openapi.schema.generation.md
guide
Documentation
- Top-level
schema.yml
with inline examples - Deployment logs API docs; grammar & header consistency pass
Portal Repo (v1.0.7)
New Features
- Blueprint Library
- New blueprint categories: "Model Serving", "Model Finetuning", "GPU Health Check", "GPU Benchmarking", "Partner Blueprints", "Platform Features" and "Other"
- Enhanced category filters; description panel moved right
- Deployments UI
- Single deployments in table view; grouped deployments in accordion
Improvements
- Robust content-type detection for Deployment-Content API with explicit error messages
Bug Fixes & Documentation
- No user-visible defects this cycle; minor doc polish
3. Cross-Repository Impact
- Unified MI300x Workflows – blueprint samples, provisioning logic, and UI entries align for seamless GPU deployments.
- Consistent Secrets Pipeline – namespaced Secrets API in Control Plane, turnkey examples in Quickstarts, and Portal-level validation.
- Blueprint Taxonomy Refresh – new categories for blueprints added; Portal surfaces "Model Serving", "Model Finetuning", "GPU Health Check", "GPU Benchmarking", "Partner Blueprints", "Platform Features" and "Other" categories for discovery.
- OpenAPI Schema – DRF-Spectacular spec underpins Quickstarts/Portal docs and simplifies client codegen.
- Local Filesystem Volumes – Quickstarts blueprints leverage new Control Plane volume declarations for high-throughput data access.
4. Upgrade Considerations
- Parameter Renames – Update any blueprint referencing
local_directory_path
tonode_directory_path
. - Terraform & Helm – Pull the latest
oci_ai_blueprints
modules; MI300x node-pool creation requires updated scripts. - Secrets API – Add the required
namespace
field to all Secrets payloads; update client libraries. - JSON Schema Updates – Validate blueprints against the updated schema (
gpu_benchmarking
,model_serving
,partner_blueprints
). - IAM & RBAC – Review updated policy examples to align roles with the new secrets and MI300x workflows.
Upgrade with confidence and enjoy streamlined MI300x GPU workflows, powerful inference benchmarking, and a richer developer experience with OCI AI Blueprints v1.0.7!
OCI AI Blueprints v1.0.6
Release Change Audit Report
New Version: v1.0.6
Previous Version: v1.0.5
Generated: 2025-08-08 11:19:51
Repositories Analyzed:
- Quickstarts Repo (oci-ai-blueprints)
- Control Plane Repo (corrino)
- Portal Repo (oci_ai_blueprints_portal)
Version v1.0.6 builds on v1.0.5 by extending hardware support, polishing developer experiences, and enriching user workflows across our Quickstarts, Control Plane (corrino), and Portal components. The centerpiece of this release is full AMD MI300x support—from plugin and metrics exporter through blueprint examples and orchestration—plus new benchmarking blueprints, secrets integration patterns, enhanced validation, and UI refinements.
-
Executive Summary
• AMD MI300x support end-to-end: new plugin, metrics exporter, example blueprints, Terraform/Helm deployment, and Control Plane manifest recognition.
• Inference benchmarking: offline & online GPU benchmarking blueprints (vLLM, LLMPerf), shareable configs, MLflow visibility.
• Secrets workflows: comprehensive, end-to-end docs and JSON recipes for opaque, container-registry, Hugging Face, and NVIDIA NIM secrets.
• Control Plane enhancements: subnet-ID & deployment-name validation, local-filesystem volumes, DRF-Spectacular OpenAPI generation, JSON-schema expansion.
• Portal UI improvements: new blueprint categories, deployments page redesign, richer error messages and parsing logic.
• Documentation uplift: updated READMEs, API docs, schema definitions, and streamlined content across all repos. -
Repository-Specific Changes
Quickstarts (oci-ai-blueprints v1.0.6)
• New Features
– AMD MI300x support: AMD plugin & metrics-exporter code, example Llama4 Maverick and shared-pool blueprints, updated RDMA table, “bring-your-own” exporter pattern.
– Offline & Online Inference Benchmarking: vLLM and LLMPerf back-ends, JSON/YAML sample configs, shareable node-pool definitions, MLflow metric logging.
– Secrets Integration: docs/secrets section with workflows and JSON recipes for generic, container-registry, HF token, and NVIDIA NIM secrets.
• Improvements
– Blueprint schema & organization: new “partner” and “gpu_benchmarking” categories; reorganized sample_blueprints folders.
– API docs: local_filesystem and input_file_system options in docs/api_documentation.md.
– Naming & clarity: local_directory_path → node_directory_path; refined offline-inference README; polished IAM policy docs.
• Technical Changes
– Terraform & Helm: added AMD metrics exporter values.yaml, updated helm.tf, locals.tf, postgres_db.tf, variables.tf; MI300x/shared-pool support in cluster_creation_terraform.
– IAM policies: refined and reorganized examples.
• Documentation
– Updated READMEs across blueprint categories.
– Added detailed docs/secrets/*.md and JSON schema.
– Removed outdated inference and Whisper-transcription docs.
– Enhanced QuickStartVersions.md, about.md, and top-level README.md.Control Plane (corrino v1.0.6)
• New Features
– AMD MI300x & local-filesystem volumes: control-plane logic and manifest templates now detect MI300x GPU deployments and allow local filesystem as I/O.
– Subnet-ID validation: new subnet_validator verifies user VCN subnet IDs.
• Improvements
– Deployment-name validation: extended for service/job modes; unit tests for shared-pool, team, and update scenarios.
– JSON schema enhancements: added “Partner Blueprints” and more blueprint categories for richer user configurations.
– Swagger/OpenAPI simplification: cleaned up api/urls.py endpoints; minor DRF endpoint header and route tweaks.
• Bug Fixes
– Resolved subnet-validator logic issue (#111).
• Technical Changes
– Model refactoring (#104): split Deployment and Manifest models; moved admin registrations into api/models/admin.py; removed old api/admin.py.
– OpenAPI with DRF-Spectacular (#92): added dependency, schema.yml, and generation README.
• Documentation
– Deployment-logs API docs (#98): examples and descriptions in api/drf/deployment.py, api/urls.py, and schema.yml.
– OpenAPI generation guide: README.openapi.schema.generation.md.
– Swagger grammar and example fixes.Portal (oci_ai_blueprints_portal v1.0.6)
• New Features
– Library page: three new blueprint categories—Partner Blueprints, Workload Blueprints, Platform Feature Blueprints.
• Improvements
– DeploymentsPage UI: flat table for individual deployments; grouped deployments in an accordion for easier scanning.
– Deployment-content component: auto-detect Content-Type (JSON vs. text), provide scenario-specific error messages.
– Library page layout: more filterable categories; moved category description panel to right side.
• No bug fixes or documentation updates in this release. -
Cross-Repository Impact
• Unified AMD MI300x support: Quickstarts deliver examples and exporter, Control Plane handles manifest detection and volume types, Terraform/Helm modules orchestrate deployment.
• End-to-end benchmarking: Quickstarts’ GPU benchmarking blueprints can be deployed via corrino with improved validation; metrics flow into MLflow for centralized monitoring.
• Shared JSON schema and categories: Quickstarts and corrino share expanded blueprint categories (“partner”, “gpu_benchmarking”), reflected in the Portal library for consistent user navigation.
• Secrets integration synergy: Quickstarts’ end-to-end examples align with Control Plane’s validation logic, ensuring secrets are correctly created, updated, and consumed in deployments.
• Documentation coherence: newly generated OpenAPI spec and schema guide supports both developer workflows in corrino and UI-driven API exploration in the Portal. -
Upgrade Considerations
• Terraform/Helm modules: review and apply updated values.yaml, helm.tf, and variables.tf to deploy the AMD device metrics exporter.
• Configuration changes
– Rename any local_directory_path settings to node_directory_path in your custom blueprints.
– Validate blueprint JSON against the new schema (added “partner” and “gpu_benchmarking” categories).
• Control Plane
– Ensure drf-spectacular and schema.yml are included in your environment to enable updated OpenAPI docs.
– Verify subnet IDs in existing deployments conform to the new subnet_validator rules to avoid validation errors.
• Portal
– No breaking changes, but note new library categories and layout adjustments.
• Secrets management
– Follow the new docs/secrets recipes when migrating existing secret workflows to the new patterns.
• IAM policies
– Update or merge in the refined examples to maintain least-privilege on AMD exporter and other new resources.
• Backward compatibility
– Existing v1.0.5 blueprints and deployments should continue to function, but it’s recommended to test in a staging environment before rolling out to production.
We recommend reviewing the detailed documentation in each repository’s v1.0.6 release notes for full migration steps, code samples, and best practices. Enjoy the expanded hardware support and richer developer experience!
OCI AI Blueprints v1.0.5
Release Change Audit Report
New Version: v1.0.5
Previous Version: v1.0.4
Generated: 2025-07-14 16:21:29
Repositories Analyzed:
- Quickstarts Repo (
oci-ai-blueprints
) - Control Plane Repo (
corrino
) - Portal Repo (
oci_ai_blueprints_portal
)
Version v1.0.5 — Release Notes (Upgrade from v1.0.4)
Release Date: 2025-07-10
1. Executive Summary
v1.0.5 introduces full support for Deployment Groups, including new sample blueprints in Quickstarts, a first-class API in Control Plane, and an accordion UI with bulk-undeploy in the Portal.
Other key updates:
- New Secrets Management API for secure credential storage
- Expanded OKE Instance Principal support in Terraform modules
- Updated Bare Metal (B200) and GPU blueprint samples
- Refined schemas, updated documentation, and multiple bug fixes for a smoother developer experience
2. Repository-Specific Changes
Quickstarts Repo (v1.0.5)
New Features
- Deployment Groups blueprint:
docs/sample_blueprints/deployment_groups/
now includesllama_stack_basic.json
and a walkthrough README - OKE Instance Principal support:
Optional in Terraform modules with new tfvars examples and schema entries
Improvements
- Llama Stack: renamed
service_url
→internal_dns_name
, streamlined JSON, updated README - Private network deployments: removed “Deploy” button, enhanced tfvars examples, better defaults
- Bare Metal (B200) & GPU: updated
shared_node_pool_B200_BM.json
, revised MIG blueprints, pinned vLLM version
Technical Changes
- Added
instance_principal
across Terraform files (locals.tf
,providers.tf
,variables.tf
, etc.) - Renamed
example_tfvars.md
→example_blueprints_tfvars.md
; addedexample_cluster_tfvars.md
- Updated
blueprint_json_schema.json
to supportdeployment_groups
andinstance_principal
Bug Fixes & Documentation
- Fixed typos in Deployment Groups README
- Updated docs in
sample_blueprints
,advanced
, andcommon_workflows
(B200, MIG, RDMA, instance principals)
Control Plane Repo (v1.0.5)
New Features
- Deployment Groups API:
- New DRF serializers, schema validators, and
AbstractExporter
interface - JSON schema and payload samples updated
- New DRF serializers, schema validators, and
- Secrets Management API:
/api/secrets/
endpoint with full CRUD- Supports secrets for environment and container registries
Improvements
- Recipes can now consume secrets; schema and tests updated
DeploymentGroupsViewSet
now returns timestamps; listing is time-sorted- Hardened
ExportCollector
andControlPlaneManager
with better error handling and validation
Bug Fixes
- Fixed edge case: “ready” deployments without exports
- Improved export collection exception handling
- Removed outdated payload (
llama-stack-real.json
)
Technical Changes
- Added
abstract_exporter
base class; replaced export enums with constants - Updated
.gitignore
and merged schemas
Portal Repo (v1.0.5)
New Features
- Accordion-style Deployment Groups UI on the Deployments page
- New “Undeploy Group” action with real-time updates and notifications
Improvements
- Confirmation prompt added to “undeploy all”
- Centralized badge and status logic
- Enhanced error logging in API proxy and utilities
Bug Fixes
- Fixed stale deployment status after undeploy
3. Cross-Repository Impact
Deployment Groups: Full End-to-End Support
- Quickstarts: hands-on blueprint samples
- Control Plane: group-aware APIs, schemas, and export logic
- Portal: group UI with bulk undeploy capability
Secrets API for Secure Credentials
- Control Plane manages secrets for environment and container registries
- Blueprint recipes now support secrets via schema changes
Unified Schema & Documentation
- Blueprint, Terraform, and Portal schemas are aligned
- Docs updated across all repos to reflect new features and parameters
4. Upgrade Considerations
Terraform Modules
- Upgrade to latest modules for
instance_principal
support - Review your
.tfvars
to reflect new schema
API & Client Updates
- Use
/api/secrets/
for managing secrets
Blueprint Versioning
- vLLM is now pinned in Llama Stack blueprints—override as needed
Enjoy the new Deployment Groups, Secrets API, and improved support for Bare Metal & GPU workloads!
OCI AI Blueprints v1.0.4
v1.0.4 — New Features
Quickstarts
Feature | What it means for you |
---|---|
Private-network deployments | Launch OKE clusters and AI Blueprints entirely inside your own VCN by supplying vcn_id , subnet_id , and related variables—no public endpoints required. |
Updated IAM & security defaults | Pre-baked policy and security-list settings make private deployments work out of the box. |
B200 / H200 + MIG shape support | Choose the latest GPU shapes for higher performance - now fully functional with OCI AI Blueprints |
Portal
Feature | Benefit |
---|---|
Archive button for deployments | Retire or hide old undeployed deployments with a single click keeping the entire deployments page clean |
Under-the-Hood Enhancements (Control Plane)
Upgrade | Why it matters |
---|---|
B200 shape & H200 MIG validation | Ensures smooth provisioning when you select these shapes for deployment in a blueprint |
Dedicated Prometheus handler | Provides more code readability and support for private network deployments |
Enjoy the new capabilities in v1.0.4!
OCI AI Blueprints v1.0.3
🚨🚨 BREAKING CHANGE – READ THIS FIRST! 🚨🚨
Upgrading to v1.0.3 will destroy all existing deployments created with earlier versions of oci-ai-blueprints
.
The upgrade replaces the Autonomous Database backend with a brand-new PostgreSQL instance, wiping the current database in the process.
Before you upgrade:
- Undeploy every active blueprint
- Back up any critical data you still need.
- Proceed with the v1.0.3 installation only after the cluster is clean.
Release Change Audit Report
New Version: v1.0.3
Previous Version: v1.0.2
Generated: 2025-06-16 10:51:07
Repositories Analyzed
- Quickstarts (
oci-ai-blueprints
) - Control Plane (
corrino
) - Portal (
oci_ai_blueprints_portal
)
Release v1.0.3 delivers our most significant infrastructure overhaul to date.
PostgreSQL becomes the default backend everywhere, a fully-fledged Llama Stack sample debuts, vLLM is bumped to0.9.1
, security & contribution guidance tighten up, and several deployment/networking issues are resolved.
The sections below give a concise—but comprehensive—overview of what changed, how the parts fit together, and what to know before you upgrade.
1 · Executive Summary
- Default Database Migration – Autonomous Database (ADB) is replaced by PostgreSQL across Quickstarts and Control Plane.
- Llama Stack Blueprint – New end-to-end sample that combines ChromaDB, Jaeger, PostgreSQL, and the Llama Stack application.
- vLLM Upgrade – All API docs, workflows, and blueprints now pin to vLLM
0.9.1
. - Documentation & Security – Added
SECURITY.md
,CONTRIBUTING.md
, richer install/verification steps, FAQs, and JSON-schema clarifications. - Bug Fixes & UX – Fixed endpoint exposure, restored proper Postgres SSL settings, added host-port overrides, improved install notes.
- Portal Repo – No changes in v1.0.3.
2 · Repository-Specific Changes
Quickstarts Repo
Category | Highlights |
---|---|
New Features | Llama Stack Blueprint • Lives under docs/sample_blueprints/llama-stack • Bundles ChromaDB, Jaeger, PostgreSQL, and the main app • Includes deployment order & structured JSON blueprint files |
Improvements | • vLLM bumped to 0.9.1 everywhere• Added SECURITY.md & CONTRIBUTING.md • Polished Installation Notes: clearer env-vars, tooling, test cmds, FAQ section |
Bug Fixes | • Corrected ingress.tf , cert-manager.tf , cluster-tools modules, policies.tf so endpoints expose correctly |
Technical Changes | • Swapped ADB ➜ PostgreSQL (postgres_db.tf , random-string creds)• Removed ADB code; updated locals.tf , outputs.tf , schema.yaml |
Documentation | • Top-level README spotlights Llama Stack blueprint• Synced sample_blueprints/README.md with new structure• Reflected vLLM bump in docs/api_documentation.md & model workflows |
Control Plane Repo
Category | Highlights |
---|---|
New Features | PostgreSQL Support • Swapped Oracle DB config for PostgreSQL in project/settings.py • Added references/postgres_db.yaml (ConfigMap, PVC, Deployment, Service)Host-Port Customization • New override in recipe_service_template.yaml • api/control_plane/digest.py now respects custom host ports |
Improvements | • Enriched combined_schema.json descriptions (recipe_container_port , recipe_host_port ) |
Bug Fixes | • Re-enabled Postgres SSL connectivity & removed unintended public LB in postgres_db.yaml |
Technical Changes | • Rolled back faulty commit f16dd51ea7f ; restored correct DB settings |
Portal Repo
No changes in this release.
3 · Cross-Repository Impact
- Unified Postgres Backend – Both Quickstarts & Control Plane deploy PostgreSQL natively; blueprints share the same manifests.
- Llama Stack Deployment – New Quickstarts blueprint spins up the full stack and leverages Control Plane’s
postgres_db.yaml
. - Consistent vLLM Versioning – Every repo now targets vLLM
0.9.1
. - Security & Contribution Alignment –
SECURITY.md
&CONTRIBUTING.md
set standards that will propagate to other repos.
4 · Upgrade Considerations
Area | Action Items |
---|---|
Database Migration | • If you are upgrading from a previous release, please make sure to undeploy all deployments before upgrading. |
Docs & Workflows | • Follow the revamped Installation Notes & FAQs in Quickstarts README .• View new documentation (updated JSON schema & API docs) regarding host/container ports. |
Security & Contribution | • Review SECURITY.md and CONTRIBUTING.md for new processes. |
Thank You for Upgrading to v1.0.3 🎉
This release lays the groundwork for a more secure, flexible, and consistent developer experience.
Encounter an issue or have feedback? Please consult SECURITY.md
and CONTRIBUTING.md
for next steps.
OCI AI Blueprints v1.0.2
Release Change Audit Report
New Version: v1.0.2
Previous Version: v1.0.1
Generated: 2025-06-03 12:30:28
Repositories Analyzed
- Quickstarts (
oci-ai-blueprints
) - Control Plane (
corrino
) - Portal (
oci_ai_blueprints_portal
)
1. Executive Summary
Version v1.0.2 brings major updates across Quickstarts, Control Plane, and Portal:
- Expanded AI blueprint library — autoscaling, CPU/GPU inference, multi-node, and RDMA-enabled deployments.
- Sub-compartment node-pool provisioning plus IAM policy enhancements in the Control Plane.
- Dynamic, versioned blueprint loading in the Portal via the new
RELEASE_VERSION
variable.
Together these features offer greater flexibility for high-performance AI inference, stronger governance across compartments, and streamlined version management.
2. Repository-Specific Changes
A. Quickstarts
Category | Details |
---|---|
New Features | Added blueprints for autoscaling inference, CPU inference (Gemma, Mistral VM/BM), GPU health checks (FP16/FP32 on A10/H100), multi-node inference, shared node pools, and RDMA clusters. Each blueprint ships with JSON definitions and a README. |
Improvements | * Terraform IAM policies now support RDMA and multi-compartment deployments. * RELEASE_VERSION injected into corrino-configmap . * Docs cleanup: renamed recipe → blueprint, flattened README hierarchy, improved formatting. |
Bug Fixes | Fixed a broken SVG in main installation docs. |
Technical Changes | * Extended Terraform locals and app-configmap module to expose RELEASE_VERSION . * Updated policies.tf for RDMA & multi-compartment rules. |
Documentation | Flattened README structure, moved version info to docs/versions , fixed links, and refreshed API & IAM guides. |
B. Control Plane
Category | Details |
---|---|
New Features | Node pools can now target specific sub-compartments. |
Improvements | Refactored image-finder logic (cluster , manager , digest , DAO modules) for faster, more reliable look-ups. Extended JSON schema to include sub-compartment fields. |
Bug Fixes | Node image filtering reliably selects compatible images. |
Technical Changes | Updated core modules (cluster.py , manager.py , digest.py ) plus DAO and data-collection handlers. Bumped combined_schema.json to reflect new fields. |
C. Portal
Category | Details |
---|---|
New Features | Introduced RELEASE_VERSION env var to control which portal/blueprint assets load at runtime. |
Improvements | lib/blueprints.ts now builds file paths from RELEASE_VERSION , enabling versioned rollouts without code edits. |
Documentation | README updated with setup steps for RELEASE_VERSION and versioned blueprint JSON naming conventions. |
3. Cross-Repository Impact
- Consistent Version Tracking —
RELEASE_VERSION
injection (Quickstarts) pairs with Portal loading logic to keep blueprints and UI in sync. - Multi-Compartment & RDMA Workflows — Control Plane sub-compartment support plus Quickstarts IAM upgrades enable secure RDMA clusters across compartments.
- Unified Blueprint Lifecycle — Docs refresh and schema bump align sample code, runtime behavior, and security posture.
4. Upgrade Considerations
Component | Action Items |
---|---|
Quickstarts | 1. Pull latest Terraform modules and apply updated policies.tf for RDMA & cross-compartment permissions.2. Add RELEASE_VERSION to your corrino-configmap .3. Sync local docs to adopt flattened README structure. |
Control Plane | 1. Deploy the new release to pick up sub-compartment parameters. 2. Ensure clients accept updated combined_schema.json . |
Portal | 1. Set/export RELEASE_VERSION in deployment manifests or CI/CD.2. Verify blueprint JSON filenames match the blueprint-vX.Y.Z.json convention. |
General | Review the consolidated IAM policy guide (docs/iam_policies.md ) and coordinate roll-outs so Portal and Quickstarts versions remain aligned. |
Thank you for adopting v1.0.2. For assistance, consult the updated documentation or contact support.
v1.0.1
Full Changelog: v1.0.1...v1.0.0
release-2025-05-16
What's Changed
- Update deployment links for 2025-04-22 release by @grantneumanoracle in #51
- Rework distributed inference docs for LWS + RDMA. by @dkennetzoracle in #49
- PR: Initial Software Versioning and Data Persistence for Services by @dkennetzoracle in #52
- Vkammari/new blueprints by @vishnukam3 in #54
- Add Kueue Helm by @grantneumanoracle in #55
- Cleaning distributed inference with ray related artifacts. by @dkennetzoracle in #53
- Update README.md by @vishnukam3 in #56
Full Changelog: release-2025-04-22...release-2025-05-16
release-2025-04-22
What's Changed
- fix 04 01 release by @grantneumanoracle in #43
- Install onto existing cluster. Users must either bring their own tool or install by @dkennetzoracle in #45
- Vkammari/doc improvements by @vishnukam3 in #46
- Add LWS Functionality + Remove Kuberay Functionality by @grantneumanoracle in #47
- Added docs and recipe samples for copying models to OCI object storage. by @dkennetzoracle in #48
Full Changelog: release-2025-04-01...release-2025-04-22
release-2025-04-01
What's Changed
- update app release to 04-01 by @grantneumanoracle in #42
Full Changelog: oci_ai_blueprints_app_release-2025-04-01...release-2025-04-01