# Blackwell Published articles for Blackwell. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## MSI XpertStation WS300 Thermals: Why a 1,300W GB300 Doesn't Throttle on a Desk DevFeed: [MSI XpertStation WS300 Thermals: Why a 1,300W GB300 Doesn't Throttle on a Desk]() Original publisher: [Read original article]() Author: Brian Beeler Published: 2026-09-14T19:41:35Z Content type: article Language: en Sources: [StorageReview.com]() Topics: [Blackwell](), [cpu](), [GPU](), [Grace CPU](), [Nvidia](), [DGX Station]() Tags: [blackwell](), [consumer](), [dgx-station](), [gpu](), [grace-cpu](), [heat](), [memory](), [nvidia](), [performance](), [review](), [workstation]() ### AI overview The article explains why MSI's XpertStation WS300 can sustain a 1,300W GB300 Grace Blackwell Ultra Superchip without throttling on a desk. It attributes the thermal stability to cold plates covering the major heat-producing components, dual 360mm radiators, multiple fans, and a cooling loop rated above the system's nominal CPU and GPU load. ### Source excerpt The most common question we got about the MSI XpertStation WS300 after our review coalesces around one key theme. The GB300 Grace Blackwell Ultra Superchip is a 1,300W part that normally lives in a liquid-cooled rack, so what happens to thermals when you put it in a tower? The concern is fair: a GB300 system The post MSI XpertStation WS300 Thermals: Why a 1,300W GB300 Doesn't Throttle on a Desk appeared first on StorageReview.com. ## Building Pinterest's VLM Serving Stack on NVIDIA Dynamo DevFeed: [Building Pinterest's VLM Serving Stack on NVIDIA Dynamo]() Original publisher: [Read original article]() Author: Pinterest Engineering Published: 2026-09-10T23:08:16Z Content type: article Language: en Sources: [Pinterest Engineering Blog - Medium]() Topics: [vlm](), [Inference](), [model-deployment](), [Orchestration](), [Latency](), [Caching](), [Open Source Models & Datasets]() Tags: [blackwell](), [cache](), [dynamo](), [embeddings](), [engineering](), [inference](), [latency](), [llm](), [multimodal](), [multimodal-ai](), [nvidia](), [nvidia-blackwell](), [open-source](), [orchestration](), [performance](), [pinterest](), [vllm](), [vlm](), [vlm-serving]() ### AI overview Pinterest describes its VLM serving stack built on NVIDIA Blackwell GPUs and NVIDIA Dynamo. The stack addresses multimodal inference demands such as image processing, variable prefill costs, KV-cache pressure, routing, and cache offloading. ### Source excerpt Lei Pan | Senior Software Engineer; Salina Wu | Senior Software Engineer; Cristian Lopez | Software Engineer I; Guangtong Bai | Staff Software Engineer; Soam Acharya | Principal Engineer; Saurabh Vishwas Joshi | Principal Engineer; Chia-Wei Chen | Staff Software Engineer; Ambud Sharma | Principal Engineer Why VLM Serving Matters at Pinterest Pinterest is a visual search and discovery platform, so its AI systems must reason over both language and visual content. Vision-language models (VLMs), which can interpret images, compare visual candidates, and respond naturally to user intent, are becoming the foundation for the next generation of Pinterest experiences: Pinterest Assistant, hybrid search, multimodal reranking, content understanding, signal generation, content safety, and more. This direction also reflects Pinterest's broader strategy to customize open-source models to meet its product & scale needs. Pinterest Assistant is a standout example. This multi-turn conversational experience covers both user language and visual content. Serving it requires low-latency VLM inference over rich multimodal context as well as reworking Qwen3-VL with proprietary multimodal embeddings to cut runtime cost while improving performance. Serving VLMs, however, introduces more challenges compared to text-only LLM workloads. Requests may carry multiple images, require extra vision encoder computation, incur larger and more variable prefill cost, and create higher KV cache pressure. To support this new class of models & product experiences, we built Pinterest's VLM serving stack on top of NVIDIA Blackwell GPUs and NVIDIA Dynamo. Blackwell GPUs incorporate many architectural innovations that are uniquely positioned for today's most demanding AI workloads -- including higher BF16/FP8 compute throughput, increased memory bandwidth, and larger HBM memory capacity -- that enable dramatically higher performance for inference. Dynamo provides a distributed inference orchestration layer that g ## Eaton HDXL Rack PDU Review: 81kW From a Single Zero-U PDU for AI Racks DevFeed: [Eaton HDXL Rack PDU Review: 81kW From a Single Zero-U PDU for AI Racks]() Original publisher: [Read original article]() Author: Brian Beeler Published: 2026-09-10T19:23:54Z Content type: comparison Language: en Sources: [StorageReview.com]() Topics: [Artificial Intelligence](), [systems](), [GPU](), [Server](), [dell](), [Nvidia](), [NVIDIA RTX](), [Blackwell]() Tags: [2026](), [ai](), [blackwell](), [dell](), [enterprise](), [gpu](), [launch](), [nvidia](), [nvidia-rtx](), [power-management](), [review](), [server](), [systems]() ### AI overview This review examines Eaton's HDXL Rack PDU G4, a zero-U power distribution unit designed to deliver 56-81 kW for high-density AI racks. It explains how GPU server power requirements, outlet counts, and redundant A/B feeds make this class of PDU necessary, using Dell PowerEdge systems with high-end accelerators as an example. ### Source excerpt Eaton is getting ready to ship the kind of PDU that didn't need to exist five years ago. The HDXL Rack PDU G4, arriving in the fourth quarter of 2026, delivers 56-81kW from a single zero-U unit, with 24 outlets, 21 branch breakers, and a 100A corded or 140A terminal-block input. Four models launch in The post Eaton HDXL Rack PDU Review: 81kW From a Single Zero-U PDU for AI Racks appeared first on StorageReview.com. ## From Wafer-Out to First Token: Codifying Supply Chain Expertise with Nemotron and Palantir Foundry DevFeed: [From Wafer-Out to First Token: Codifying Supply Chain Expertise with Nemotron and Palantir Foundry]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-09-10T09:00:00Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [datacenter](), [networking](), [Software](), [data]() Tags: [agentic-ai-generative-ai](), [ai-agent](), [blackwell](), [compute](), [cuopt](), [data-center](), [gb200](), [infrastructure](), [llms](), [manufacturing](), [memory](), [nemo](), [nemotron](), [networking](), [nvidia](), [nvidia-blackwell](), [nvl72](), [performance](), [production](), [real-time](), [software](), [supply-chain](), [vera-rubin]() ### AI overview NVIDIA describes how it measures and reduces the time from wafer-out to first token across complex Grace Blackwell and Vera Rubin supply chains. The article focuses on time-to-rack, critical material allocation, real-time visibility, redundancy, reliability, and codifying human expertise. ### Source excerpt NVIDIA has one of the largest and most complex supply chains in the world, and its performance is measured from wafer-out to first token. The interval is in two... ## HP ZGX Fury Is Now Orderable: GB300 Superchip, 748GB Unified Memory, and a Red Hat AI Factory Plan for the Edge DevFeed: [HP ZGX Fury Is Now Orderable: GB300 Superchip, 748GB Unified Memory, and a Red Hat AI Factory Plan for the Edge]() Original publisher: [Read original article]() Author: Brian Beeler Published: 2026-09-09T19:35:12Z Content type: news Language: en Sources: [StorageReview.com]() Topics: [Artificial Intelligence](), [Inference](), [Blackwell](), [GPU](), [Nvidia](), [DGX Station](), [Grace CPU](), [Hardware](), [Fine-tuning](), [Availability](), [NVLink](), [NCCL]() Tags: [10gbe](), [ai](), [ai-factory](), [availability](), [blackwell](), [connectx](), [consumer](), [dgx-station](), [fine-tuning](), [gpu](), [grace-cpu](), [hardware](), [inference](), [nvidia](), [nvlink](), [nvme](), [red-hat](), [usb](), [workstation]() ### AI overview HP's ZGX Fury AI station is available to order with a GB300 Grace Blackwell Ultra Desktop Superchip, 748GB of unified memory, and up to 20 petaFLOPS of FP4 compute. HP positions it as a shared inference system for departments, factory floors, and branch offices, supported by a collaboration with Red Hat and NVIDIA to run Red Hat AI Factory with NVIDIA. ### Source excerpt HP's ZGX Fury AI station is now available to order, and HP paired the availability news with a collaboration with Red Hat and NVIDIA to put Red Hat AI Factory with NVIDIA on top of it. The ZGX Fury is HP's take on NVIDIA's DGX Station design, built around the GB300 Grace Blackwell Ultra Desktop The post HP ZGX Fury Is Now Orderable: GB300 Superchip, 748GB Unified Memory, and a Red Hat AI Factory Plan for the Edge appeared first on StorageReview.com. ## DGX Spark Windows Clue: This Week's Firmware Adds a Windows Boot Certificate as NVIDIA Details October RTX Spark PCs DevFeed: [DGX Spark Windows Clue: This Week's Firmware Adds a Windows Boot Certificate as NVIDIA Details October RTX Spark PCs]() Original publisher: [Read original article]() Author: Brian Beeler Published: 2026-09-05T00:25:04Z Content type: news Language: en Sources: [StorageReview.com]() Topics: [DGX Spark](), [Windows](), [boot](), [Blackwell](), [Arm]() Tags: [arm](), [blackwell](), [boot](), [consumer](), [dgx-spark](), [secure-boot](), [update](), [windows](), [workstation]() ### AI overview A firmware update for a DGX Spark cluster added the Windows UEFI CA certificate, suggesting groundwork for Windows support on the platform. The article explains the certificate's role in UEFI Secure Boot and notes that Windows on this hardware would still require drivers, an installer, and broader platform support. NVIDIA has announced October Windows PCs using the same GB10-class silicon under the RTX Spark name. ### Source excerpt NVIDIA used IFA in Berlin to put Windows at the center of its local AI story. The company's September 3 post covers a new Windows Agent framework for agents that run in the background under OS control, one-click Windows setups for OpenClaw and Nous Research's Hermes Agent, a beta of an inference router called NVIDIA The post DGX Spark Windows Clue: This Week's Firmware Adds a Windows Boot Certificate as NVIDIA Details October RTX Spark PCs appeared first on StorageReview.com. ## Hot Chips 2026: Intel's Crescent Island DevFeed: [Hot Chips 2026: Intel's Crescent Island]() Original publisher: [Read original article]() Author: George Cozma Published: 2026-08-27T05:12:31Z Content type: article Language: en Sources: [Chips and Cheese]() Topics: [intel](), [GPU](), [Artificial Intelligence](), [datacenter](), [Blackwell](), [deepseek]() Tags: [2026](), [ai](), [amd](), [blackwell](), [datacenter](), [deepseek](), [gpu](), [intel]() ### AI overview The article discusses Intel's upcoming Crescent Island datacenter GPU, focusing on its LPDDR5X-based memory subsystem, reported capacity of up to 480 GB, undisclosed memory bandwidth, Xe3P architecture, and full-rate FP64 support. It also compares aspects of the design with competing GPUs. ### Source excerpt Hello you fine Internet folks, ## NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Watt DevFeed: [NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Watt]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-08-24T15:00:05Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [AI-assisted coding]() Tags: [agentic-ai](), [agentic-ai-generative-ai](), [agentic-coding](), [ai-agent](), [ai-agents](), [ai-factory](), [ai-infrastructure](), [benchmark](), [blackwell](), [cache](), [cloud-networking](), [cloud-services](), [data-center-cloud](), [gb300-nvl72](), [hardware](), [inference](), [long-context](), [mixture-of-experts-moe](), [nemotron](), [nvidia](), [performance](), [software-defined-data-center](), [tools](), [vera-rubin](), [vera-rubin-nvl72]() ### AI overview The article examines the SemiAnalysis AgentX benchmark for measuring infrastructure efficiency on replayed agentic coding sessions. It compares Vera Rubin and Blackwell NVL72 systems by agentic throughput per megawatt and explains why dynamic, stateful sessions require more realistic evaluation than fixed-length inference tests. ### Source excerpt AI agents have expanded inference from single-turn interactions into multi-step workflows that reason, invoke tools, coordinate subagents, and carry growing... ## NVIDIA Exemplar Cloud: Lessons for Unlocking Full Performance on AI Infrastructure DevFeed: [NVIDIA Exemplar Cloud: Lessons for Unlocking Full Performance on AI Infrastructure]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-07-30T16:00:00Z Content type: tutorial Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [debugging](), [Processes]() Tags: [ai](), [ai-infrastructure](), [benchmarks](), [blackwell](), [cloud](), [cloud-services](), [cpu](), [data-center-cloud](), [debugging](), [developer-tools-techniques](), [dgx-cloud](), [diagnostics](), [distributed-training](), [featured](), [gb200](), [gb300-nvl72](), [grace-cpu](), [hardware](), [hopper](), [infiniband](), [infrastructure](), [kernel](), [linux](), [nvidia](), [nvl72](), [performance](), [training]() ### AI overview A troubleshooting guide for closing AI-training throughput gaps between NVIDIA reference architectures and partner clusters. It covers configuration and installation issues across memory management, CPU power and NUMA placement, NCCL queue-pair concurrency, and hardware setup. ### Source excerpt Two AI computing clusters built from identical NVIDIA H100, GB200 NVL72, or GB300 NVL72 systems can deliver materially different training throughput. We... ## Inside NVIDIA Rubin GPU Architecture: Powering the Era of Agentic AI DevFeed: [Inside NVIDIA Rubin GPU Architecture: Powering the Era of Agentic AI]() Original publisher: [Read original article]() Author: Eduardo Alvarez Published: 2026-07-21T18:15:00Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [GPU](), [Nvidia](), [Artificial Intelligence](), [Inference](), [Inference Performance](), [long-context](), [datacenter](), [Transformer](), [Deployment]() Tags: [accelerate](), [agentic](), [agentic-ai](), [agentic-ai-generative-ai](), [ai](), [ai-agent](), [ai-factory](), [ai-inference](), [architecture](), [blackwell](), [cache](), [compute](), [data-center](), [data-center-cloud](), [developer-tools-techniques](), [dsx](), [efficiency](), [featured](), [gpu](), [inference](), [inference-performance](), [latency](), [long-context](), [memory](), [mixture-of-experts-moe](), [nvfp4](), [nvidia](), [rubin-gpu](), [scale](), [tensor-cores](), [top-stories](), [training](), [vera-rubin]() ### AI overview This article examines the NVIDIA Rubin GPU architecture and its co-designed Vera Rubin platform for agentic AI inference. It describes how Tensor Cores, HBM4 memory, the Transformer Engine, NVFP4 performance, cache, decoding, and scale-up systems address throughput, latency, long-context execution, and rack-scale deployment. ### Source excerpt What began as discrete AI model training and human-facing chat interfaces has evolved into always-on AI factories dedicated to producing intelligence at scale.... ## Lessons From the Leaderboard: What 5,000+ Kagglers Taught Us About Improving AI Reasoning DevFeed: [Lessons From the Leaderboard: What 5,000+ Kagglers Taught Us About Improving AI Reasoning]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-07-14T18:20:32Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [Artificial Intelligence](), [Benchmark](), [Chain-of-thought](), [datasets](), [Cloud](), [Google](), [NCCL]() Tags: [agentic-ai-generative-ai](), [ai](), [ai-agent](), [ai-inference](), [benchmark](), [blackwell](), [chain-of-thought](), [cost](), [deep-learning](), [engineering](), [evaluation](), [featured](), [google](), [kaggle](), [lora](), [nemotron](), [nvidia](), [performance](), [pre-trained-foundation-models](), [synthetic](), [techniques]() ### AI overview The article distills lessons from NVIDIA's Nemotron Model Reasoning Challenge, where more than 5,000 Kaggle participants tested ways to improve AI reasoning under shared model, infrastructure, and evaluation constraints. It highlights synthetic chain-of-thought data, trace quality, targeted solvers, validation beyond public leaderboards, and careful training and context-budget management. ### Source excerpt The NVIDIA Nemotron Model Reasoning Challenge invited the Kaggle community to explore a focused question: What techniques can improve reasoning accuracy when... ## Reducing High-Bandwidth Memory Bottlenecks in JAX-Based LLM Training with Host Offloading DevFeed: [Reducing High-Bandwidth Memory Bottlenecks in JAX-Based LLM Training with Host Offloading]() Original publisher: [Read original article]() Author: Tanya Lenz Published: 2026-07-10T18:17:40Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [LLM Techniques](), [Large Language Model](), [GPU](), [Mixture of Experts (MoE)](), [cpu](), [NVLink](), [systems](), [Nvidia]() Tags: [agentic-ai-generative-ai](), [blackwell](), [compute](), [cpu](), [developer-tools-techniques](), [featured](), [gb200](), [gpu](), [grace-cpu](), [large-language-model](), [llm](), [llm-techniques](), [mixture-of-experts-moe](), [nvidia](), [nvl72](), [nvlink](), [simulation-modeling-design](), [training-ai-models](), [vera-rubin](), [work]() ### AI overview This article explains how host offloading in JAX-based large language model training reduces GPU high-bandwidth memory pressure by moving selected activations to pinned host memory and streaming them back during the backward pass. It discusses activation-transfer overlap, NVIDIA Grace Blackwell and GB200 NVL72 systems, and experiments involving Llama 3.1 405B and DeepSeek-V3 671B. ### Source excerpt Large language model (LLM) training workloads increasingly run into GPU memory limits before compute is fully used. Model weights, gradients, optimizer states,... ## Enhancing Goodput in Large-Scale LLM Training with Nonuniform Tensor Parallelism DevFeed: [Enhancing Goodput in Large-Scale LLM Training with Nonuniform Tensor Parallelism]() Original publisher: [Read original article]() Author: Michelle Horton Published: 2026-07-06T21:44:23Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [GPU](), [Large Language Model](), [Training AI Models](), [LLM Techniques](), [NVLink](), [Availability](), [Hardware](), [Network](), [systems](), [Nvidia]() Tags: [ai](), [ai-training](), [availability](), [blackwell](), [data-center-cloud](), [developer-tools-techniques](), [efficiency](), [featured](), [gpu](), [hardware](), [llm](), [llm-techniques](), [mlops](), [network](), [nvidia](), [nvidia-blackwell](), [nvlink](), [performance](), [scale](), [training](), [work]() ### AI overview This article explains how Nonuniform Tensor Parallelism can improve Goodput in large-scale LLM training by adapting tensor parallelism to changing GPU availability and overlapping data resharding. The experimental approach aims to reduce interruptions, lost throughput, and computational waste in tightly interconnected GPU clusters. ### Source excerpt Training LLMs at massive scale brings unique infrastructure challenges, especially as jobs span thousands of GPUs and run for extended periods. The longer these... ## Hardware-Rooted AI Security That Won't Slow You Down DevFeed: [Hardware-Rooted AI Security That Won't Slow You Down]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-07-02T21:25:42Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [Cryptography](), [Inference Performance]() Tags: [agentic-ai-generative-ai](), [ai](), [ai-agent](), [ai-inference](), [ai-security](), [benchmarks](), [blackwell](), [cloud-services](), [code-software-generation](), [data-center-cloud](), [dynamo-triton](), [encryption](), [featured](), [gpu](), [hardware](), [inference-performance](), [latency](), [nvlink](), [security](), [security-for-ai](), [software-defined-data-center](), [tensorrt](), [tensorrt-llm](), [trustworthy-ai-cybersecurity]() ### AI overview An overview of NVIDIA Confidential Computing for protecting AI inference workloads, including hardware-rooted attestation and encryption. It reports benchmark results of up to 98% of the inference performance of configurations without confidential-computing security. ### Source excerpt AI has transformed how organizations operate, driving unprecedented levels of productivity and innovation. However, AI adoption can be impeded by concerns... ## Ubuntu Server on the NVIDIA DGX Spark (Without the Desktop) DevFeed: [Ubuntu Server on the NVIDIA DGX Spark (Without the Desktop)]() Original publisher: [Read original article]() Author: Techno Tim Published: 2026-06-22T13:00:00Z Content type: tutorial Language: en Sources: [Techno Tim]() Topics: [DGX Spark](), [Ubuntu](), [NVIDIA DGX](), [GPU](), [NVLink](), [CUDA](), [Docker](), [Ansible](), [vllm](), [Blackwell](), [networking](), [GitHub]() Tags: [ai](), [ansible](), [blackwell](), [cuda](), [dell](), [dgx-spark](), [docker](), [github](), [gpu](), [homelab](), [networking](), [nvidia-dgx](), [nvlink](), [ubuntu](), [vllm]() ### AI overview A guide to replacing DGX OS with a minimized Ubuntu 24.04 Server installation on GB10 systems such as the NVIDIA DGX Spark and ASUS Ascent GX10. It explains the memory and power benefits of removing GNOME while retaining the NVIDIA drivers, CUDA, Docker, and NVIDIA Container Toolkit, and covers ConnectX-7 networking, dual-node setup, and Ansible automation. ### Source excerpt When you buy an NVIDIA DGX Spark or an ASUS Ascent GX10, it ships with DGX OS. DGX OS is NVIDIA's managed Ubuntu image, and it is fine - if you want a full GNOME desktop on an AI box. I did not want that. The GB10 has 128 GB of unified memory shared between the CPU and GPU over NVLink-C2C. Every gigabyte the OS and desktop environment consume is a gigabyte not available to your model. On the ... ## GPU-Accelerated Remote Desktop on Linux from macOS - the Hard Way DevFeed: [GPU-Accelerated Remote Desktop on Linux from macOS - the Hard Way]() Original publisher: [Read original article]() Author: Techno Tim Published: 2026-04-13T13:00:00Z Content type: tutorial Language: en Sources: [Techno Tim]() Topics: [GPU](), [Linux](), [Ubuntu](), [macOS](), [Nvidia](), [CUDA](), [Blackwell](), [Latency](), [Microsoft]() Tags: [blackwell](), [cuda](), [gpu](), [homelab](), [latency](), [linux](), [macos](), [microsoft](), [nvidia](), [ubuntu]() ### AI overview This article documents the troubleshooting process for achieving GPU-accelerated H264 encoding over RDP from Ubuntu 24.04 ARM64 systems with NVIDIA GB10 Grace-Blackwell hardware to macOS. It compares xrdp's software-rendering path with GNOME Remote Desktop's CUDA-backed encoding and describes connection problems encountered with Microsoft's Windows App on macOS. ### Source excerpt What started as "just set up RDP" turned into an all day rabbit hole about how Linux remote desktop actually works, why most of it doesn't work with NVIDIA on ARM64, and what it actually takes to get GPU-accelerated H264 encoding over RDP from an Ubuntu machine to a Mac. What I was trying to do I have two ASUS Ascent GX10 machines running Ubuntu 24.04. They are ARM64 systems built around th... ## DigitalOcean Announces GPU Droplets Accelerated by NVIDIA HGX B300 DevFeed: [DigitalOcean Announces GPU Droplets Accelerated by NVIDIA HGX B300]() Original publisher: [Read original article]() Author: Waverly Swinton Published: 2025-12-15T17:51:51Z Content type: release Language: en Sources: [DigitalOcean]() Topics: [Digital Ocean](), [GPU](), [Blackwell](), [Nvidia](), [virtual machines](), [High-Performance Computing](), [Inference](), [Cloud](), [Generative AI](), [data analytics](), [Multi-GPU](), [long-context]() Tags: [ai](), [blackwell](), [compute](), [digitalocean](), [gpu](), [high-performance-computing](), [inference](), [infrastructure](), [long-context](), [multi-gpu](), [nvidia](), [product-updates](), [real-time]() ### AI overview DigitalOcean announces GPU Droplets accelerated by NVIDIA HGX B300, describing the platform's intended benefits for AI training, inference, generative AI, data analytics, and high-performance computing workloads. ### Source excerpt AI continues to evolve at an unprecedented pace, with new models and demanding workloads pushing the boundaries of what's possible. From complex large language models (LLMs) to intricate scientific simulations, developers and businesses need access to the most powerful and efficient computing infrastructure. At DigitalOcean, we're committed to providing the cutting-edge tools you need to build, deploy, and scale your AI initiatives with simplicity and affordability. That's why we're excited to announce that GPU Droplets accelerated by NVIDIA HGX™ B300 are coming soon to DigitalOcean, marking a significant upgrade to our GPU offerings. Why NVIDIA HGX™ B300? The NVIDIA Blackwell Ultra accelerated computing platform represents a leap forward in AI reasoning. Designed for both training and inference, the NVIDIA HGX B300 offers substantial improvements in computational power, memory bandwidth, and energy efficiency compared to previous generations. The NVIDIA Blackwell architecture at the heart of the HGX B300 is not just about raw power; it's also about efficiency and innovation. With 1.5X more dense Tensor Core FLOPS, enhanced attention performance, and significantly expanded memory, the HGX B300 is optimized for the most demanding AI workloads including generative AI, data analytics, and high-performance computing (HPC). Featuring 7X more AI compute than NVIDIA Hopper platforms, 2.1TB of HBM3e memory, and high-performance networking integration with NVIDIA ConnectX-8 SuperNICs, Blackwell Ultra delivers breakthrough performance on the most complex workloads from agentic systems and reasoning, to real-time video generation. For AI-native enterprises running large reasoning models and long-context workloads, this enables: -Reduced model offloading and improved time-to-first-token -Higher sustained throughput under concurrency -More efficient multi-GPU scaling -Improved tokens-per-second per dollar Unlike GPU capacity providers, DigitalOcean integrates inference-optimized ## An AI Engineer's Guide To Choosing GPUs DevFeed: [An AI Engineer's Guide To Choosing GPUs]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2025-12-07T14:02:40Z Content type: tutorial Language: en Sources: [Neural Bits]() Topics: [GPU](), [Nvidia](), [Hardware](), [Machine learning](), [Artificial Intelligence](), [Inference](), [Large Language Model](), [Blackwell](), [Hopper](), [lora](), [NCCL](), [Kernel]() Tags: [ai](), [ai-engineer](), [architecture](), [blackwell](), [clusters](), [compute](), [data-center](), [deep-dive](), [gpu](), [guide](), [hardware](), [hopper](), [inference](), [llm](), [ml](), [nvidia](), [nvlink](), [pcie](), [software](), [technical]() ### AI overview A technical guide to choosing NVIDIA GPUs for AI workloads. It explains how GPU microarchitecture, memory subsystems, form factors, and interconnects affect capabilities, scaling, training, and inference, and compares consumer and data-center GPUs. ### Source excerpt A deep dive on technical Hardware and Software details of NVIDIA GPUs for AI Workloads. ## Introducing Mistral 3 DevFeed: [Introducing Mistral 3]() Original publisher: [Read original article]() Published: 2025-12-02T16:00:00Z Content type: release Language: en Sources: [Mistral AI Blog]() Topics: [AI Models](), [Open Source Models & Datasets](), [Mixture of Experts (MoE)](), [Open Source](), [Nvidia](), [NVFP4](), [vllm](), [Blackwell]() Tags: [apache](), [blackwell](), [mistral](), [mixture-of-experts](), [models](), [nvfp4](), [nvidia](), [open](), [open-source](), [vllm]() ### AI overview Mistral announces Mistral 3, a family of open models including compact dense models and Mistral Large 3, a sparse mixture-of-experts model with 41B active and 675B total parameters. The models are released under Apache 2.0, with compressed formats and optimized checkpoints intended to improve accessibility, customization, and deployment across developer and enterprise environments. ### Source excerpt The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.