Releases: intel/intel-technology-enabling-for-openshift
Releases · intel/intel-technology-enabling-for-openshift
Intel Enterprise AI Foundation for OpenShift
We are thrilled to announce the release of Intel Enterprise AI Foundation for OpenShift (Intel Technology Enabling for OpenShift) version 2.0.0.
What’s new in version 2.0.0
1.Architecture Update for Intel Enterprise AI Foundation
2.RoCE Networking‐Based LLM Post‐Training Solution with Intel Enterprise AI Foundation for OpenShift
- Comprehensively outline the vision, architecture, and end-to-end solution for Intel Enterprise AI foundation on Red Hat's AI platform.
- Boldly predict a key industry trend: the growing importance of post-training optimization to enhance Large Language Model performance while reducing model size for domain-specific deployment.
- To address this trend, combine Intel AI hardware and software technologies with Red Hat's production-grade AI platform to deliver a competitive, end-to-end solution for modern GenAI workloads - including LLM inferencing and post-training optimization - tailored for enterprise AI usages.
Known issues
Intel® Technology Enabling for OpenShift* version 1.6.1
We are thrilled to announce the release of Intel Technology Enabling for OpenShift version 1.6.1 for Red Hat OpenShift 4.18.
What’s new in version 1.6.1
- Intel Device Plugin Operator and the related device plugins are upgraded to v0.32.1
- Intel® QuickAssist Technology (Intel® QAT) multiple Custom Resources support with Node Selector
Known issues
- On OCP-4.18, node rebooting might fail due to the bug and RedHat provided workaround for this issue.
Intel® Technology Enabling for OpenShift* version 1.6.0
We are thrilled to announce the release of Intel Technology Enabling for OpenShift version 1.6.0 for OpenShift 4.18.
What’s new in version 1.6.0
- OpenShift 4.18 supported added
- Intel® Data Center GPU Flex Series provisioning feature is added back with
- Intel Data Center GPU Driver for OpenShift 3.0.0 version
Known issues
• On OCP-4.18, Node rebooting might fail due to the bug and RedHat provided workaround for this issue.
Intel® Technology Enabling for OpenShift* version 1.5.2
We are thrilled to announce the release of Intel Technology Enabling for OpenShift version 1.5.2 Release
What’s new in version 1.5.2
- Integrate the Gaudi Software 1.19
- Prototype of vLLM with Intel Gaud 1.19.1 support for OpenShift
- Prototype of Provisioning Gaudi with Intel Gaudi AI Accelerator Operator
- Prototype of upgrading SPI firmware with Gaudi Software 1.19
- QAT Readme enhancement
Known Issue
- Intel Data Center GPU Flex and Max Series provisioning of the out of tree driver support is for the RHEL 9.2 kernel and OpenShift (OCP) 4.12.6 through OCP 4.15. Support for the RHEL s kernel will be available in a later release.
Intel® Technology Enabling for OpenShift* version 1.5.1
We are thrilled to announce the release of Intel Technology Enabling for OpenShift version 1.5.1 Release
What’s new in version 1.5.1
- Intel® Gaudi® Software 1.18.0-524 integrated with Intel Enterprise AI Foundation on OCP-4.16.25. Intel Gaudi Software 1.19.0 integration will be completed in next release.
- Prototype of Intel® Gaudi® SPI firmware upgrade support for Single Node OpenShift
- Prototype of vLLM with Intel Gaudi support for OpenShift
- Intel Gaudi platform network scale up verification process for OpenShift
- Intel Gaudi platform hardware and firmware support verification process for OpenShift
- Developer Preview of One stop online document
About this release
1.5.1 release includes the below General Available features:
- Intel® Software Guard Extensions (Intel® SGX) provisioning
- Intel® QuickAssist Technology (Intel® QAT) provisioning
- Intel AI inference end-to-end (E2E) solution based on:
- OpenVINO™ Operator that simplifies managing optimized deep learning inference at scale in OpenShift
- Red Hat OpenShift AI
- Intel® Data Center GPU Flex Series provisioning for RHEL 9.2 kernel and OpenShift 4.15
Developer preview features:
- One stop online document
- Intel Gaudi platform network scale up testing support for OpenShift
- Gaudi Platform hardware and firmware support check for OpenShift
- Media feature provisioning for Intel Data Center GPU
- Intel® Data Streaming Accelerator (Intel® DSA) provisioning
- One-click solution to provision the Intel Gaudi accelerator
Prototype features:
- Intel Gaudi Software 1.18.0-524 integrated with Intel Enterprise AI Foundation on OCP-4.16.25.
- Gaudi SPI FW upgrade support for Single Node OpenShift
- vLLM with Intel Gaudi support for OpenShift
- Intel technology features for Enterprise AI foundation availability are continuously verified on OpenShift releases using the Red Hat Distributed Continuous Integration (DCI) based CI/CD pipeline
Known Issue
- Intel Data Center GPU Flex and Max Series provisioning of the out of tree driver support is for the RHEL 9.2 kernel and OpenShift (OCP) 4.12.6 through OCP 4.15. Support for the RHEL 9.4 kernel will be available in a later release.
Intel® Technology Enabling for OpenShift* version 1.5.0
We are thrilled to announce the release of Intel Technology Enabling for OpenShift version 1.5.0 for OpenShift 4.17.
What’s new in version 1.5.0
- Supporting OCP-4.17
- Intel Gaudi Base Operator 1.18 integrated with Intel Enterprise AI Foundation on OCP-4.16.10
About this release
1.5.0 release includes the below General Available features:
- Intel® Data Center GPU Flex Series provisioning
- Intel® Software Guard Extensions (Intel® SGX) provisioning
- Intel® QuickAssist Technology (Intel® QAT) provisioning
- Intel AI inference E2E solution based on
- OpenVINO™ Operator that simplifies managing optimized deep learning inference at scale in OpenShift
- Red Hat OpenShift AI
- Intel Data Center GPU Flex Series provisioning
Developer Preview feature:
- Intel Data Center GPU Max Series provisioning
- Media feature provisioning for Intel Data Center GPU
- Intel Data Streaming Accelerator (DSA) provisioning
- One-Click solution to provision Intel Gaudi Accelerator
Prototype feature:
- One Stop Online Document
- Intel Gaudi Base Operator 1.18 integrated with Intel Enterprise AI Foundation on OCP-4.16.10
Intel technology features for Enterprise AI foundation availability continuously verified on OpenShift release using DCI based CI/CD pipeline
Intel® Technology Enabling for OpenShift* version 1.4.0
We are thrilled to announce the release of Intel Technology Enabling for OpenShift version 1.4.0 for OpenShift 4.16.
What’s new in version 1.4.0
- Developer Preview Intel® Data Streaming Accelerator (DSA) provisioning on OCP-4.16.13+
- Intel Device Plugin Operator and the related device plugins are upgraded to v0.29.1
- Developer Preview One-Click solution to provision the Gaudi accelerator with Intel enterprise AI foundation on OCP-4.16.10+
- Intel Gaudi Base Operator 1.17 integrated with Intel Enterprise AI Foundation on OCP-4.16.10
About this release
1.4.0 release includes the below General Available features:
- Intel® Data Center GPU Flex Series provisioning
- Intel® Software Guard Extensions (Intel® SGX) provisioning
- Intel® QuickAssist Technology (Intel® QAT) provisioning
- Intel AI inference E2E solution based on
- OpenVINO™ Operator that simplifies managing optimized deep learning inference at scale in OpenShift
- Red Hat OpenShift AI
- Intel Data Center GPU Flex Series provisioning
Developer Preview feature:
- Intel Data Center GPU Max Series provisioning
- Media feature provisioning for Intel Data Center GPU
- Intel Data Streaming Accelerator (DSA) provisioning
- One-Click solution to provision Intel Gaudi Accelerator
Prototype feature:
- One Stop Online Document
- Intel Gaudi Base Operator 1.17 integrated with Intel Enterprise AI Foundation on OCP-4.16.10
Intel technology features for Enterprise AI foundation availability continuously verified on OpenShift release using DCI based CI/CD pipeline
Intel® Technology Enabling for OpenShift* version 1.3.1
We are thrilled to announce the release of Intel Technology Enabling for OpenShift version 1.3.1 with
enablement of OPEA ChatQnA prototype workloads with Intel® Gaudi AI accelerator provisioning on Intel enterprise AI foundation for OpenShift 4.14.
What’s new in version 1.3.1
- OPEA ChatQnA workload prototype integrated and running with Intel enterprise AI foundation for OpenShift
- Intel Gaudi AI accelerator provisioning integrated with Intel enterprise AI foundation for OpenShift
- Prototype of Red Hat Operator and Ansible based one-click solution for provisioning the Intel Gaudi AI accelerator with OpenShift
About this release
General Availability features:
- Intel® Data Center GPU Flex Series provisioning
- Intel® Software Guard Extensions (Intel® SGX) provisioning
- Intel® QuickAssist Technology (Intel® QAT) provisioning
- Intel AI inference E2E solution based on
- OpenVINO™ operator that simplifies managing optimized deep learning inference at scale with OpenShift
- Red Hat OpenShift AI
- Intel Data Center GPU Flex Series provisioning
Developer Preview features:
- Intel Data Center GPU Max Series provisioning
- Media feature provisioning for Intel Data Center GPU
Prototype features:
- One stop program documentation
- Red Hat operator and Ansible based one-click solution
- One-click solution for provisioning Intel Gaudi AI accelerator with OpenShift
- Red Hat operator and Ansible based one-click solution for provisioning Intel Gaudi AI accelerator with OpenShift
- Intel Gaudi AI accelerator Provisioning integrated with Intel Enterprise AI Foundation for OpenShift
Intel technology features availability is continuously verified on OpenShift releases using the Red Hat Distributed CI (DCI) based CI/CD pipeline.
Intel® Technology Enabling for OpenShift* version 1.3.0
We are thrilled to announce the release of Intel Technology Enabling for OpenShift version 1.3.0 for OpenShift 4.15.15+.
What’s new in version 1.3.0
- Intel Device Plugin Operator and the related device plugins are upgraded to v0.29.0.
- Intel Data Center GPU Driver for OpenShift is upgraded to v2.2.0.
- Developer Preview of Media feature provisioning for Intel® Data Center GPU.
- Prototype of one stop online documentation publishing.
- Prototype of Red Hat Operator and Ansible based One-Click solution.
About this release
General Available features:
- Intel® Data Center GPU Flex Series provisioning
- Intel® Software Guard Extensions (Intel® SGX) provisioning
- Intel® QuickAssist Technology (Intel® QAT) provisioning
- Intel AI inference E2E solution based on
- OpenVINO™ Operator that simplifies managing optimized deep learning inference at scale in OpenShift
- Red Hat OpenShift AI
- Intel Data Center GPU Flex Series provisioning
Developer Preview feature:
- Intel Data Center GPU Max Series provisioning
- Media feature provisioning for Intel® Data Center GPU
Prototype feature:
- One Stop Online Document
- Red Hat Operator and Ansible based One Click solution.
Intel technology features availability continuously verified on OpenShift release using DCI based CI/CD pipeline.
Fixed issues
NFD SGX EPC extended resource support issue
Intel® Technology Enabling for OpenShift* version 1.2.1
We are thrilled to announce the release of Intel Technology Enabling for OpenShift version 1.2.1 for OpenShift 4.14.11+.
What’s new in version 1.2.1
- Fast GPU provisioning supported
With the prebuilt Intel Data Center GPU driver container images managed by the KMM Operator and Intel Data Center GPU bootless technology, provisioning of Intel GPUs is reduced from more than three minutes to less than one second for each node on OpenShift. This provisioning improvement enhances the Intel Data Center GPU scale-out performance and simplifies the scale-out and on-demand allocation of the GPU resources (see Fast-GPU-Provisioning-Technology). - Developer Preview Intel® Data Center GPU Max Series
- Bootless GPU provisioning, see issue 34
- Reduced driver container image size, see issue 33
- Previously released Intel features are now continuously verified with each new OpenShift release allowing for features to be always available.
- Intel Data Center GPU Driver for OpenShift is upgraded to v2.2.0.
- Includes the use of Red Hat OpenShift AI* v2.8.0
About this release
1.2.1 release includes the below General Available features:
- Intel® Data Center GPU Flex Series provisioning
- Intel® Software Guard Extensions (Intel® SGX) provisioning
- Intel® QuickAssist Technology (Intel® QAT) provisioning
- Intel AI inference E2E solution based on
- OpenVINO™ Operator that simplifies managing optimized deep learning inference at scale in OpenShift
- Red Hat OpenShift AI
- Intel Data Center GPU Flex Series provisioning
Developer Preview feature:
- Intel Data Center GPU Max Series provisioning