Agent Substrate: Advancing Kubernetes for Agents at Scale
AI agents spend most of their time idle, waiting on a human prompt, a tool result or a model response. Kubernetes wasn’t built for that. Running one Pod per...
Five Ways NVIDIA Co-Design Maximizes the Value of Every Byte in the AI Factory
In an AI factory, high bandwidth memory (HBM)is the fastest, most expensive, and most contested memory tier. Every byte spent on a redundant weight copy, an...
Build a Validated Kubernetes Runtime for NVIDIA Dynamo
Teams building AI applications need a repeatable path from a model configuration to a working inference endpoint. NVIDIA Dynamo is a distributed inference...
Scale Agentic Coding Workflows with Meta’s Muse Spark Open on NVIDIA GB300 NVL72
Meta launches Muse Spark Open, a coding-optimized 816B mixture-of-experts (MoE) model with 42B active parameters and a 1M token context window. Trained on...
AICR v1.0: Open, stable, and verifiable GPU cluster configuration
GPU-accelerated Kubernetes clusters depend on compatible versions across dozens of components, each on its own release cycle: host kernels, GPU drivers,...
Deploying an HSTU Generative Recommender with NVIDIA Dynamo-Triton
Generative recommender (GR) systems are emerging as a powerful new approach for large-scale personalization. Instead of treating recommendation as a set of...
How NVIDIA DSX MaxLPS Maximizes AI Factory Throughput and Efficiency
Every unused watt is capacity left on the table. AI factories are typically provisioned for the unlikely moment when every GPU reaches peak power, creating a...
Simplifying Model Serving Across Multiple GPUs with NVIDIA TensorRT Multi-Device Integration in NVIDIA Dynamo-Triton
The compute and memory demands of generative AI increasingly exceed what a single GPU can provide. NVIDIA TensorRT multi-device inference is a new capability...
When to Use Encode-Prefill-Decode Disaggregation to Accelerate Multimodal Model Serving
Encode-prefill-decode (EPD) disaggregation is an inference optimization technique for multimodal models that separates the vision encoder stage from the...
Introducing CUDA Rust: Two Tracks for Writing GPU Kernels
In September 2026, NVIDIA announced it is leaning into native GPU programming in Rust. CUDA C++ and CUDA Python are mature, enterprise-grade toolchains, and...
Restore LLM Inference Capacity in Seconds with Shadow Engine Recovery in NVIDIA Dynamo
When an LLM engine process fails, the standard recovery path involves a cold restart. This requires loading weights into HBM from storage, compiling kernels,...
NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Watt
AI agents have expanded inference from single-turn interactions into multi-step workflows that reason, invoke tools, coordinate subagents, and carry growing...
Maximizing AI Factory Performance per Watt with NVIDIA DSX MaxLPS
AI factories are power-constrained industrial systems. The question is no longer how many GPUs fit in a data center, but how much AI output each available...
Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300 NVL72
Alibaba released the open weights for Qwen3.8-2.4T-A95B (Qwen3.8-Max), its largest open-weight model, bringing near-frontier capabilities to the open...
ModelExpress: Distributing Model Artifacts at the Speed of Light
Every byte moved has a cost. As model checkpoints grow to hundreds of gigabytes or even a terabyte, that cost adds up quickly. To make things even worse,...
