Topic

The systems
behind useful
intelligence.

Compute, inference, data, observability, and the technical foundations that make reliable AI possible.

Compute  /  Reliability  /  Scale

Open computer hardware with CPU cooling, memory modules, graphics accelerators, and connected processing units arranged on a workbench overlooking mountains at sunset.
AI Infrastructure4 min read

ONNX Runtime 1.30 expands generative AI inference across CUDA, WebGPU and CPUs

The release broadens attention, decoding and quantization support, but several CUDA paths remain hardware-specific or opt-in and CPU FP16 execution now depends on acceleration.

Sep 10, 2026
4 min read
AI-generated editorial illustration: An industrial data center at dusk, a robotic arm carefully rearranging plain unmarked server modules.
AI Infrastructure10 min read

HyperPod InstantStart Turns Complex SageMaker Operations Into Guarded Agent Workflows

The open-source control plane gives infrastructure teams a web interface, REST APIs and an AI agent backed by the same validation, reconciliation and persisted state for…

Sep 06, 2026
10 min read
AI-generated editorial illustration: Macro photography of a silver processor with many colored light paths across a dark silicon surface.
AI Infrastructure9 min read

SGLang v0.5.19 expands model support, inference performance and hardware reach

The release combines 786 pull requests from 214 contributors, adding nine model entries, beam search, DeepEP v2, broader speculative decoding, unified caching, diffusion improvements and extensive…

Sep 06, 2026
9 min read
AI-generated editorial illustration: A robotic hand learning to grasp a red cube in an industrial studio, with a mirrored physical twin.
AI Infrastructure13 min read

How NVIDIA Cosmos 3 and SageMaker HyperPod Power a Physical AI Model Factory

AWS outlines a persistent, shared GPU architecture for synthetic data generation, distributed post-training, and closed-loop evaluation, with end-to-end GPU goodput—not isolated job throughput—as the central operating…

Sep 06, 2026
13 min read
AI-generated editorial illustration: An aerial view of the Australian coastline at sunrise, subtle fiber-optic light trails reaching an unmarked coastal data center.
AI Infrastructure8 min read

OpenAI GPT-5.6 reaches Australian Amazon Bedrock Regions through global inference

AWS has opened access to GPT-5.6 Sol, Terra, and Luna through Amazon Bedrock endpoints in Sydney and Melbourne, with three API paths, prompt caching, federated Codex…

Sep 03, 2026
8 min read
AI-generated editorial illustration: A compact exposed GPU on a wooden desk beside a closed unbranded laptop, soft amber light, suggesting powerful local computation in a small device.
AI Infrastructure7 min read

Hugging Face Releases 207 WebGPU Kernels for Local AI in the Browser

The new @huggingface/kernels JavaScript library loads versioned GPU operations from the Hugging Face Hub, while Fleet gathers browser-based performance and correctness evidence across real-world hardware.

Sep 02, 2026
7 min read