hardware

arXiv:2608.07964v1 Announce Type: cross Abstract: Load Balancing has emerged as a critical problem in expert-parallel distributed inference of Mixture-of-Experts (MoE) models. As routing distributions

arXiv:2608.08761v1 Announce Type: cross Abstract: In an era defined by escalating climate change and the pervasive deployment of edge intelligence, the environmental cost of semiconductor manufacturin

arXiv:2608.08531v1 Announce Type: new Abstract: Deep learning-driven representations such as neural radiance fields (NeRFs) and 3D Gaussian splatting (3DGS) have revolutionized the field of dynamic 3D

arXiv:2608.08522v1 Announce Type: new Abstract: Event-based vision is becoming an increasingly important sensing paradigm for robotics, yet its adoption remains limited by sensor availability and the

arXiv:2607.18171v2 Announce Type: replace Abstract: Real-time multimodal applications, including voice agents and interactive video generation, compose heterogeneous models into pipelines whose effici

arXiv:2608.09450v1 Announce Type: new Abstract: Betting-based sequential tests and Blackwell approachability are linked by a rate-explicit reduction through support-function residuals. For a compact c

arXiv:2608.07707v1 Announce Type: new Abstract: Computing distances between sets is essential in robotic motion planning and control, where differentiable gradients enable real-time optimization. The

Anhata Rooprai / Reuters: IBM and Together AI sign a 240M, multi-year deal to build an AI inference cluster on IBM Cloud, using Nvidia's HGX B300 systems, to support open-source models — IBM (IBM.N) a

arXiv:2512.20968v2 Announce Type: replace-cross Abstract: Distributed attention is essential for scaling large language models (LLMs) to long contexts, yet existing methods either have limited paralle

In August 2026, Together AI entered into a multi‑year partnership with IBM and NVIDIA to deliver enterprise‑grade open‑source AI inference on IBM Cloud. The collaboration deploys a dedicated NVIDIA B3

As inference becomes the dominant workload in AI infrastructure, multi-tier storage architectures are emerging as a key method for cost control and enhanced performance. These architectures combine fl

🦔Nvidia announced agreements yesterday with the six biggest names in private capital, Apollo, Blackstone, BlackRock, Brookfield, Goldman Sachs, and KKR, to raise over $500 billion so its own customers

NVIDIA JetPack 7.2.1 adds agentic video skills with the unified jetson‑videosdk, allowing programmable, device-aware video workflows that link developer intent to live device discovery and performance

https://github.com/NVIDIA-NeMo/Switchyard Finally an open source LLM router. An alternative to openrouter fusion and Sakana Fugu. Doesn't look like it does exactly what Sakana Fugu does according to i

Some of Wall Street’s biggest financial firms are partnering with Nvidia Corp. to pour a half-trillion dollars of funding into the artificial intelligence industry’s massive infrastructure buildout. N

River AI Inc., a startup that helps enterprises customize open-source artificial intelligence models, has raised 1.1 billion in early-stage funding. The company stated in today’s announcement that it

arXiv:2608.08363v1 Announce Type: cross Abstract: Silicon carbide (SiC) power modules are increasingly deployed in automotive traction inverters, where condition monitoring is essential to prevent in-

arXiv:2608.07580v1 Announce Type: new Abstract: In this work, we present a wildfire temperature retrieval framework for VSWIR imaging spectroscopy data, employed on data from NASA's Airborne Visible I

NVIDIA NeMo Switchyard is a routing platform that directs AI agent workloads to the most suitable specialized or frontier model for each step of a task, balancing performance, cost, and latency. It of

arXiv:2603.02637v2 Announce Type: replace-cross Abstract: Modern machine learning (ML) workloads increasingly rely on GPUs, yet achieving high end-to-end performance remains challenging due to depende

arXiv:2608.09160v1 Announce Type: new Abstract: Query-Key Normalization (QK-Norm) improves the training stability and quality of modern Large Language Models (LLMs). However, under Tensor Parallelism

Together AI is teaming up with @IBM and @nvidia to bring enterprise-grade AI inference to IBM Cloud. A dedicated NVIDIA B300 cluster. Spectrum-X networking. First of its kind on IBM Cloud, powered by

arXiv:2608.09537v1 Announce Type: new Abstract: Foundation world models have made remarkable progress in planning, simulation, and embodied intelligence. However, optimizing a pretrained world model t

arXiv:2608.08287v1 Announce Type: new Abstract: GPU language comparisons are almost always run on tiled dense linear algebra, where every toolchain is good and the differences are small. We implement

Every new generation of accelerated computing demands more from the infrastructure underneath it — more compute performance, higher rack density and more efficient, scalable power distribution. The bo

2/ New deep dive: Autoscaling endpoints for LLM inference. Dedicated Inference can scale on eight metrics. inflight_requests is the default because it sees queue pressure before latency degrades. We t

arXiv:2608.06412v1 Announce Type: cross Abstract: Understanding which surfaces in a scene are physically accessible to a given tool is fundamental for robotic interaction, yet 3D perception systems ty

arXiv:2608.06763v1 Announce Type: new Abstract: Weight quantization for large-language-model inference must balance adaptive reconstruction levels with representations regular enough for efficient GPU

arXiv:2608.06912v1 Announce Type: new Abstract: The top-k operation is a fundamental building block of modern sparse computation, enabling token routing, expert activation, memory selection, and atten

On August 10 2026 at 1:39 AM UTC, user Itamar Friedman (@itamar_mar) posted a short tweet asking whether Anthropic’s potential launch of its own chips would prompt NVIDIA to release frontier AI models

Jensen Huang just told the incredible story of how Elon Musk became NVIDIA’s first customer for its AI supercomputer - when literally nobody else wanted it “When I announced this thing, nobody wanted

Vlad Savov / Bloomberg: Meta says Muse Glimmer has 30B parameters and is “small enough” to need only one GPU; Meta plans a $1B fund to invest in US communities near its data centers — Meta Platforms I

Financial Times: Nvidia partners with Apollo, BlackRock, Blackstone, Brookfield, Goldman Sachs, and KKR on a $500B funding package for AI infrastructure development — Apollo, Blackstone and Goldman Sa

arXiv:2608.07078v1 Announce Type: cross Abstract: Flexible macromolecular docking offers high-fidelity predictions of biomolecular interactions, but remains prohibitively expensive at scale. Among exi

Bloomberg: Sources: AI cloud computing provider Lambda is selling a $917M leveraged loan to finance the purchase of GPUs as part of a contract with Nvidia — Lambda Inc., an AI cloud-computing provider

arXiv:2608.06959v1 Announce Type: new Abstract: Modern Earth observation (EO) satellites carry increasingly advanced sensors that produce vast volumes of high-resolution, multispectral data, yet downl

The TileRT InferenceX article (Aug 10 2026) examines whether the TileRT software stack on NVIDIA GPUs can compete with dedicated inference systems such as Cerebras, Groq LPUs and SambaNova for ultra‑h

Ultra-High Interactivity on NVIDIA GPUs? TileRT InferenceX Can TileRT software on NVIDIA GPU compete with Cerebras, Groq LPU, SambaNova? Batch Size 1, Disaggregated engine, High throughput prefill eng

The past week I've been running DSv4 inference on my laptop by keeping everything RAM-resident except the MXFP4-experts (since expert pool is ~147GB and won't fit) TL;DR - read speed is the limiter mo

I am not a meteorologist, but I just read a very interesting article: https://arstechnica.com/science/2026/08/deepminds-hurricane-model-bought-forecasters-an-extra-day/ In a paper published on Thursda

arXiv:2512.02551v4 Announce Type: replace-cross Abstract: In this paper, we propose CUDA-L2, a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically optimi

arXiv:2608.06088v1 Announce Type: new Abstract: Robotics simulators serve as a foundational infrastructure for embodied AI, facilitating safe and scalable robotic system development. NVIDIA Isaac Sim

arXiv:2608.05819v1 Announce Type: new Abstract: Classical simulation remains essential for developing and validating quantum algorithms, but its cost grows rapidly with circuit size. Tensor-network co

arXiv:2608.06146v1 Announce Type: new Abstract: End-to-end document parsers provide a unified interface, but serialize page layouts and regional contents into one autoregressive sequence. This formula

arXiv:2603.10711v3 Announce Type: replace Abstract: Real-time solution of nonlinear optimal control problems remains challenging on embedded robotic hardware, where conventional solvers often rely on

The Information: Sources: Nvidia agrees to invest 2B in Lancium, the power infrastructure developer of the Stargate campus in Texas, plus 1B more if it hits certain thresholds — Nvidia has agreed to i