Knowledge catalogue
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
Mackenzie Hawkins / Bloomberg: Sources: the US Commerce Department's BIS is reviewing how Chinese AI companies access Nvidia chips overseas, including by legally renting foreign data centers — A key U
arXiv:2608.05109v1 Announce Type: cross Abstract: Significance. Accurate intraoperative depth perception is important for autonomous and semi-autonomous robotic laparoscopic surgery. Conventional frin
Advanced Micro Devices Inc. said today it has agreed to buy Taalas Inc., a Toronto startup that hardwires artificial intelligence models directly into silicon, in a deal that pushes the chipmaker deep
Tobias Mann / The Register: AMD acquires Toronto-based Taalas, which integrates model weights directly into silicon to boost inference performance, for an undisclosed sum — Early tech demos show model
arXiv:2608.04041v1 Announce Type: new Abstract: Open-World Learning (OWL) pipelines for oil well anomaly detection have recently been shown to combine autoencoder-based detection, multiclass classific
arXiv:2608.04956v1 Announce Type: new Abstract: Recent video models increasingly support generation, reference conditioning, and editing within a single model, yet typically expose them as separate op
Anna Tong / Forbes: Docs: US data labeling companies, like Surge AI and Mercor, that sell training datasets to US AI labs and the government are also selling them to Chinese labs — The same Silicon Va
arXiv:2608.04612v1 Announce Type: new Abstract: We present GASP, a GPU-Accelerated Safe Planner for real-time, collision-aware joint-space motion generation in known environments. GASP combines a clam
arXiv:2507.04004v3 Announce Type: replace Abstract: This paper presents the first photo-realistic LiDAR-Inertial-Camera Gaussian Splatting SLAM system that simultaneously addresses visual quality, geo
Hugging Face Storage Buckets are now on http://Vast.ai Connect your HF Storage Bucket as a Cloud Connection in your Vast settings, and every GPU instance you rent can pull datasets and checkpoints str
In July, NVIDIA joined more than 200 companies and organizations in signing “Open Weights and American AI Leadership,” an open letter arguing that AI leadership will be measured not by any single fron
Melissa Hancock / Fortune: Ooredoo, Nvidia, Nokia, and Indosat launch Zankore, Indonesia's first dedicated AI compute and neocloud platform; Ooredoo, which owns a 49% stake, commits $800M — Ooredoo Gr
arXiv:2608.04842v1 Announce Type: new Abstract: Replicating real-world environments into simulation by realistic visual representation like NeRF and 3D Gaussian Splatting (3DGS) has emerged as an effe
arXiv:2608.05033v1 Announce Type: cross Abstract: Sparse matrix kernels are fundamental to scientific computing, graph analytics, and machine learning. Their GPU performance depends strongly on the in
arXiv:2608.04811v1 Announce Type: new Abstract: Structured pruning enhances the efficiency of deep neural networks (DNNs) by eliminating groups of parameters during inference. Previous methods mostly
Nichiket Sunil / Reuters: Sydney-based AI data center company Firmus raised 2B in funding from Coatue, Nvidia, and others at a 10.5B post-money valuation, up from 5.5B in April — Firmus said on Friday
arXiv:2602.14010v2 Announce Type: replace-cross Abstract: Pathology foundation models (PFMs) generalize well across computational pathology tasks but remain costly for gigapixel whole-slide image anal
arXiv:2608.03695v1 Announce Type: cross Abstract: This work addresses community detection in temporal networks through GPU-accelerated extensions of spectral clustering and modularity-based algorithms
arXiv:2608.02989v1 Announce Type: cross Abstract: Speculative decoding verifies a tree of draft tokens in one target-model forward pass. For a mixture-of-experts (MoE) target, however, parallel verifi
arXiv:2504.06881v2 Announce Type: replace-cross Abstract: Convolutional neural networks (CNNs) are foundational to many state-of-the-art computer vision systems, yet their reliance on multiplication-i
arXiv:2608.03696v1 Announce Type: new Abstract: This work focuses on the problem of learning on temporal graphs, with particular emphasis on the task of clustering: obtaining coarse-grained representa
arXiv:2608.03701v1 Announce Type: cross Abstract: World-action modeling has emerged as a promising paradigm for robotic control, as it empowers models to go beyond reacting to observations and anticip
arXiv:2608.03036v1 Announce Type: cross Abstract: Large Language Models (LLMs) are integrated into software systems and AI services, making efficient LLM serving a concern for software engineering. Se
Setup: GPU: RTX 3090 24GB RAM: 32GB ComfyUI 0.30.0 PyTorch 2.13.0+cu130 CUDA 13.0 SageAttention enabled (sageattention-2.2.0+cu130torch2.10.0andhigher.post6-cp310-abi3-win_amd64) Spectrum node + Euler
arXiv:2608.00130v1 Announce Type: cross Abstract: Fortran has been the cornerstone of high-performance computing for decades and remains unmatched in many domains. Yet the language faces an expertise
Dina Bass / Bloomberg: AI cloud startup Volta Infra raised 300M led by a16z and Altimeter at a 2.4B valuation and says it landed a 10B contract with an unnamed leading AI developer — Volta Infra Holdi
AI compute is going to orbit. 🚀 @SpaceX’s Starmind AI1 satellite compute payload is powered by NVIDIA Vera Rubin NVL72, bringing AI factory compute closer to the stars. The next chapter of AI infrastr
Surging AI demands are driving the need for massive datasets and context windows that burst past the confines of system memory. But rising needs aren’t met by simply adding more storage capacity. What
arXiv:2608.01651v1 Announce Type: cross Abstract: Hybrid-attention large language models combine full attention with recurrent linear attention to reduce long-context inference costs, yet their autore
Compute scarcity is not the only struggle AI teams face. Optimal utilization is also key. Friction also emerges when they outgrow informal coordination methods such as shared spreadsheets, manual SSH
early sparks of rsi? Ali Taha @waterloo_intern explains how http://Z.ai's GLM-5.2 (@Zai_org) profiled its SGLang serving path and rewrote bottlenecked GPU kernels, (still lacks reliable judgment) grea
NVIDIA Alpamayo 2 Super is a publicly available 34‑billion‑parameter vision–language–action model that merges a 32‑B Cosmos 3 Super Reasoner with a 2‑B action‑expert diffusion network. It produces uni
I'm hoping that one of you guys has been working on an inference engine or has somehow found improvements to running DSV4F on RDNA4 multi-GPU setups. I am currently building a custom inference engine
arXiv:2608.00577v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models have become a dominant architecture for large-scale AI services, yet deploying them over geo-distributed heterogeneous
arXiv:2608.01127v1 Announce Type: new Abstract: Video world models predict future observations conditioned on historical observations and control signals, enabling long-horizon generation through auto