Red Hat unveils big enhancements to Red Hat Enterprise Linux AI

Red Hat’s rapid AI innovation: Red Hat has unveiled significant enhancements to its Red Hat Enterprise Linux AI (RHEL AI) platform, releasing version 1.2 just weeks after the initial 1.0 launch.

• RHEL AI is designed to streamline generative AI model development, testing, and deployment, with a focus on making large language model (LLM) training more affordable and accessible.
• The platform combines IBM Research’s open-source Granite LLM family, InstructLab alignment tools, and a collaborative approach to model development.
• RHEL AI utilizes Retrieval-Augmented Generation (RAG) to enhance the accuracy of AI responses by accessing approved external knowledge sources.

Key improvements in RHEL AI 1.2:

• Expanded hardware support now includes Lenovo ThinkSystem SR675 V3 servers with factory preload options for faster deployment.
• A technology preview introduces support for AMD Instinct Accelerators, including MI300x GPUs for training and inference, and MI210 GPUs for inference tasks.
• Cloud platform compatibility has been extended to Azure and Google Cloud Platform, in addition to existing support for AWS and IBM Cloud.

Software enhancements and efficiency gains:

• The new “Periodic Checkpointing” feature allows users to save long training runs at regular intervals during fine-tuning, enabling resumption from the last saved checkpoint.
• PyTorch Fully Sharded Data Parallel (FSDP) technology preview dramatically reduces training times for multi-phase model training with synthetic data.
• FSDP shards a model’s parameters, gradients, and optimizer states across parallel workers, significantly cutting training times.

Democratizing AI development: RHEL AI aims to make LLM training more accessible to programmers and subject matter experts, not just data scientists.

• Joe Fernandes, Red Hat’s Foundation Model Platform vice president, emphasizes the platform’s ability to enable domain experts to contribute to purpose-built gen AI models across hybrid cloud environments.
• The platform allows IT organizations to scale these models for production through Red Hat OpenShift AI.

Rapid iteration and market positioning:

• With the release of version 1.2, Red Hat is deprecating support for version 1.1, giving users 30 days to upgrade.
• This quick succession of releases underscores Red Hat’s aggressive push into the enterprise AI market and reflects the accelerating pace of AI development.

Looking ahead: The rapid evolution of RHEL AI demonstrates the intense competition and innovation in the enterprise AI space, with potential implications for the broader adoption and development of AI technologies in business environments.

• As AI development continues to accelerate, companies may need to adapt quickly to keep pace with new capabilities and platforms.
• The focus on making AI more accessible to non-data scientists could lead to more diverse and specialized AI applications across various industries.