# NeMo NVIDIA NeMo is a modular software suite of APIs and libraries for building, deploying, and optimizing AI agents, including an open-source Python framework for generative AI models. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Presentation: Decision Models in Agentic Architectures: From Production to Agent Skills DevFeed: [Presentation: Decision Models in Agentic Architectures: From Production to Agent Skills]() Original publisher: [Read original article]() Author: Alex Porcelli Published: 2026-09-14T11:00:00Z Content type: article Language: en Sources: [InfoQ]() Topics: [Agent Skills](), [Artificial Intelligence](), [Large Language Model](), [NeMo]() Tags: [agent](), [agent-skills](), [agentic](), [agentic-ai-architecture](), [agents](), [ai](), [ai-architecture](), [ai-ml-data-engineering](), [architecture](), [architecture-design](), [architectures](), [artificial-intelligence](), [business](), [decision-models-agentic-ai](), [development](), [enterprise](), [enterprise-architecture](), [governance](), [infoq](), [large-language-models](), [llms](), [ml-data-engineering](), [models](), [nemo](), [presentation](), [production](), [qcon-ai-boston-2026](), [qcon-software-development-conference](), [skills](), [transcripts]() ### AI overview Alex Porcelli explains how DMN decision models can be integrated with LLMs, agent skills, and NeMo guardrails to create auditable and deterministic agentic architectures for high-stakes enterprise decisions. ### Source excerpt Alex Porcelli discusses the critical gap in enterprise AI: non-deterministic output and lack of accountability in high-stakes decisions. He shares how integrating DMN decision models with LLMs, agent skills, and NeMo guardrails creates auditable, deterministic agentic architectures - allowing business leaders to own decision logic while engineers maintain robust architectural governance. By Alex Porcelli ## Deploy NeMo Guardrails on Red Hat OpenShift AI DevFeed: [Deploy NeMo Guardrails on Red Hat OpenShift AI]() Original publisher: [Read original article]() Author: Rob Geada Published: 2026-09-09T15:05:01Z Content type: tutorial Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [NeMo](), [Deployment](), [ai safety](), [Open Source](), [prompt injection]() Tags: [article](), [deployment](), [developer](), [how-to](), [nemo](), [open-source](), [operator](), [platform](), [prompt-injection](), [red-hat](), [safety](), [security]() ### AI overview This tutorial explains how to deploy an evaluated NeMo Guardrails configuration on a Red Hat OpenShift AI cluster. It covers prerequisites, creating a ConfigMap from the configuration files, and creating a NeMoGuardrails custom resource for a managed deployment. ### Source excerpt This is part 3 in a 3-part series on local guardrail development and evaluation. In the 1st article, I looked at how to design and develop a guardrail configuration on a local machine, and then tried some manual testing. In the 2nd article, I explored how to rigorously test a guardrail against popular large-scale risk datasets. The post Deploy NeMo Guardrails on Red Hat OpenShift AI appeared first on Red Hat Developer. ## Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding DevFeed: [Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding]() Original publisher: [Read original article]() Author: Michelle Horton Published: 2026-08-26T17:07:12Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [qwen](), [long-context](), [Mixture of Experts (MoE)](), [agentic-coding](), [Inference](), [GPU](), [multimodal](), [NeMo](), [sglang](), [TensorRT-LLM](), [vllm](), [rust-ai]() Tags: [agentic-ai-generative-ai](), [agentic-coding](), [benchmarks](), [context-window](), [developer-tools-techniques](), [gb300-nvl72](), [inference](), [mixture-of-experts-moe](), [multimodal](), [nemo](), [nvlink](), [qwen](), [sglang](), [tensorrt-llm](), [top-stories](), [vllm]() ### AI overview This NVIDIA developer article introduces Qwen3.8-Flash-Next, a multimodal mixture-of-experts model released by Alibaba for experimentation and evaluation. It explains the model's long-context hybrid architecture, including Gated DeltaNet and Qwen Sparse Attention, and discusses reported efficiency improvements for million-token workloads. The article also covers inference support through SGLang, vLLM, TensorRT-LLM, and NVIDIA NeMo, plus performance on the NVIDIA GB300 NVL72 platform. ### Source excerpt Alibaba released the model weights for Qwen3.8-Flash-Next as a preview of the upcoming Qwen4 architecture for developers to experiment with and evaluate. It's... ## The future of AI-native Is open source DevFeed: [The future of AI-native Is open source]() Original publisher: [Read original article]() Author: Sam Barlien Published: 2026-07-23T05:40:01Z Content type: opinion Language: en Sources: [Platform Engineering Blog]() Topics: [Open Source](), [AI Infrastructure](), [Platform Engineering](), [Nvidia](), [Dynamo](), [NeMo](), [rocm](), [Linux](), [OpenClaw]() Tags: [ai-infrastructure](), [linux](), [nemo](), [nvidia](), [open-source](), [openclaw](), [platform-engineering](), [rocm]() ### AI overview The article argues that AI infrastructure is undergoing a structural shift as NVIDIA and AMD open-source software for running and optimizing their hardware. It presents this as a platform engineering decision: ecosystem adoption and open software stacks may matter more than proprietary software control. ### Source excerpt Chip vendors like NVIDIA and AMD are open sourcing the software that runs their AI hardware. Here is why that shift is a platform engineering decision. ## Deploy a Production-Ready NVIDIA AI-Q Blueprint on Oracle Cloud Infrastructure DevFeed: [Deploy a Production-Ready NVIDIA AI-Q Blueprint on Oracle Cloud Infrastructure]() Original publisher: [Read original article]() Author: Anurag Kuppala Published: 2026-06-26T19:00:45Z Content type: tutorial Language: en Sources: [NVIDIA Technical Blog]() Topics: [Artificial Intelligence](), [Terraform](), [Kubernetes](), [Cloud](), [LangChain](), [Retrieval Augmented Generation (RAG)](), [NeMo](), [API keys]() Tags: [agentic-ai-generative-ai](), [ai](), [ai-agent](), [ai-agents](), [api-keys](), [data-center-cloud](), [featured](), [kubernetes](), [langchain](), [nemo](), [oracle](), [rag](), [terraform]() ### AI overview A tutorial for deploying the open-source NVIDIA AI-Q 2.0 multi-agent blueprint on Oracle Cloud Infrastructure. It uses Terraform to provision OCI resources and Helm to install workloads on OKE, resulting in an AI-Q endpoint with a teardown command. ### Source excerpt AI agents have changed a lot in the last two years. The first could only answer one question at a time. Then came multi-turn chat, where the model could keep... ## Accelerating Transformers Fine-Tuning with NVIDIA NeMo AutoModel DevFeed: [Accelerating Transformers Fine-Tuning with NVIDIA NeMo AutoModel]() Original publisher: [Read original article]() Author: Adil Asif; Alexandros Koumparoulis; Wenwen Gao; Sylendran Arunagiri; David Messina; Bernard Nguyen Published: 2026-06-24T16:00:13Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [NeMo](), [Fine-tuning](), [AI Models](), [Mixture of Experts (MoE)](), [distributed-training](), [Generative AI](), [Artificial Intelligence](), [GPU](), [PyTorch](), [vllm](), [sglang]() Tags: [ai](), [ai-models](), [building](), [compute](), [distributed-training](), [fine-tuning](), [framework](), [generative](), [generative-ai](), [gpu](), [infrastructure](), [kernels](), [memory](), [model](), [moe](), [nemo](), [nemotron](), [nvidia](), [open](), [transformers]() ### AI overview This article explains how NVIDIA NeMo AutoModel accelerates fine-tuning of mixture-of-experts models by extending Transformers v5 with Expert Parallelism, DeepEP fused all-to-all dispatch, and TransformerEngine kernels. It describes API compatibility, distributed execution, dynamic weight loading, and reported gains of 3.4-3.7x higher training throughput and 29-32% lower GPU memory use. ### Source excerpt NVIDIA NeMo AutoModel is an open library part of the NVIDIA NeMo framework for building custom generative AI models at scale. NeMo AutoModel builds cleanly on top of v5, adding Expert Parallelism, DeepEP fused all-to-all dispatch, and TransformerEngine kernels, and it leans on v5's dynamic weight loading to bring those optimizations to a broad and growing set of model families. ## Build a Domain-Specific Embedding Model in Under a Day DevFeed: [Build a Domain-Specific Embedding Model in Under a Day]() Original publisher: [Read original article]() Author: Steve Han; Rucha Apte; Sean Sodha; Oliver Holworthy Published: 2026-03-20T19:38:16Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [Fine-tuning](), [synthetic-data](), [Synthetic Data Generation](), [Model Development](), [Inference](), [model-deployment](), [NeMo](), [Nemotron](), [NVIDIA NIM](), [TensorRT](), [Claude](), [API keys]() Tags: [api](), [fine-tuning](), [gpu](), [inference](), [nemo](), [nemotron](), [nim](), [nvidia](), [nvidia-nim](), [synthetic](), [synthetic-data](), [synthetic-data-generation]() ### AI overview A tutorial showing how to fine-tune a general-purpose embedding model for a specific domain in less than a day using synthetic question-answer pairs generated from domain documents. It covers data generation, contrastive training, retrieval evaluation, and deployment, using NVIDIA NeMo components and a Llama-Nemotron embedding model. ### Source excerpt With a single GPU and less than a day of training time, you can transform a general-purpose embedding model into one that truly understands your domain, no manual labeling required. To help you hit the ground running, we are also releasing a ready-to-use synthetic training dataset generated from NVIDIA's public documentation using this exact pipeline. ## Mistral AI partners with NVIDIA to accelerate open frontier models DevFeed: [Mistral AI partners with NVIDIA to accelerate open frontier models]() Original publisher: [Read original article]() Published: 2026-03-16T20:00:00Z Content type: news Language: en Sources: [Mistral AI Blog]() Topics: [Artificial Intelligence](), [Nvidia](), [foundation-models](), [Open Source](), [Nemotron](), [Fine-tuning](), [Model Development](), [NVIDIA DGX](), [DGX Cloud](), [Synthetic Data Generation](), [model architecture](), [NeMo]() Tags: [ai](), [dgx-cloud](), [fine-tuning](), [foundation-models](), [models](), [multimodal](), [nemo](), [nemotron](), [nvidia](), [open](), [optimization](), [post-training](), [synthetic](), [synthetic-data-generation]() ### AI overview Mistral AI announces a partnership with NVIDIA and its founding membership in the NVIDIA Nemotron Coalition. The collaboration will develop open frontier AI models using Mistral AI's model expertise and NVIDIA's compute, development tools, and synthetic-data pipelines. The coalition's first initiative will support the NVIDIA Nemotron 4 family, while Mistral AI also releases Mistral Small 4 for developers, researchers, and organizations. ### Source excerpt The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models. ## The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator DevFeed: [The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator]() Original publisher: [Read original article]() Author: Seph Mard; Isabel Hulseman; Besmira Nushi; Piotr Januszewski; Grzegorz Chlebus; VivienneZhang; Wojciech Prazuch; Pablo Ribalta; Nik Spirin; Ferenc Galko Published: 2025-12-17T13:22:18Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [LLM evaluation / benchmarking](), [Benchmark](), [NeMo](), [Nemotron](), [Artificial Intelligence](), [Nvidia](), [configuration](), [Library](), [Inference]() Tags: [ai](), [benchmark](), [benchmarking](), [benchmarks](), [build](), [configuration](), [evaluation](), [inference](), [library](), [model](), [models](), [nemo](), [nemotron](), [nvidia](), [open](), [pipeline](), [pipelines](), [reuse](), [validation](), [verify]() ### AI overview This article presents an open, reproducible evaluation recipe for NVIDIA Nemotron 3 Nano 30B A3B using the NeMo Evaluator library. It explains how complete configurations, prompts, runtime settings, harness versions, logs, and artifacts enable independent verification and consistent model comparisons across inference backends and infrastructure. ### Source excerpt NVIDIA released Nemotron 3 Nano 30B A3B with an explicitly open evaluation approach to make that distinction clear. Alongside the model card, we are publishing the complete evaluation recipe used to generate the results, built with the NVIDIA NeMo Evaluator library, so anyone can rerun the evaluation pipeline, inspect the artifacts, and analyze the outcomes independently. We believe that open innovation is the foundation of AI progress. ## Nemotron-Personas-India: Synthesized Data for Sovereign AI DevFeed: [Nemotron-Personas-India: Synthesized Data for Sovereign AI]() Original publisher: [Read original article]() Author: Kiran Praveen; Utkarsh Vaidya; Evan A; Lipika Ramaswamy; Dhruv Nathawani; Dane Corneil; Yev Meyer Published: 2025-10-13T23:00:42Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Artificial Intelligence](), [Synthetic Data Generation](), [synthetic-data](), [datasets](), [Sovereign AI](), [NeMo](), [Nemotron](), [LLMs]() Tags: [ai](), [ai-adoption](), [data](), [datasets](), [evaluation](), [generation](), [india](), [language](), [llms](), [model](), [models](), [nemo](), [nemotron](), [nvidia](), [open-source](), [synthetic](), [synthetic-data](), [synthetic-data-generation]() ### AI overview NVIDIA releases Nemotron-Personas-India, an open synthetic dataset of Indic personas designed to address the lack of multilingual and culturally representative data for Indian AI systems. Built with NeMo Data Designer and licensed under CC BY 4.0, it contains 21 million personas across English and Hindi in Devanagari and Latin scripts, with demographic, geographic, occupational, and cultural attributes. ### Source excerpt India represents one of the world's largest AI opportunities -- with over 700 million internet users, a multitude of languages, and a rapidly growing developer ecosystem. Yet, most open datasets reflect Western norms and English-only contexts, creating a data gap that limits AI adoption in India's multilingual, multi-script environment. ## Nemotron-Personas-Japan: ソブリン AI のための合成データセット DevFeed: [Nemotron-Personas-Japan: ソブリン AI のための合成データセット]() Original publisher: [Read original article]() Author: Atsunori Fujita; Masaya Ogushi; Vincent Gong; Kotaro Yamamoto; Yoshi Suhara; Dane Corneil; Yev Meyer Published: 2025-09-26T06:25:50Z Content type: article Language: ja Sources: [Hugging Face - Blog]() Topics: [datasets](), [Nemotron](), [Artificial Intelligence](), [data](), [Large Language Model](), [NeMo](), [Nvidia](), [gpt-oss](), [pii](), [Pydantic]() Tags: [ai](), [apache](), [data](), [gpt-oss](), [japan](), [llm](), [nemo](), [nemotron](), [nvidia](), [oss](), [pii]() ### AI overview NVIDIA has released Nemotron-Personas-Japan, an open synthetic dataset of Japanese personas designed to support culturally grounded and privacy-preserving AI development. Built with NeMo Data Designer, it contains six million Japanese-language personas aligned with Japanese demographic, geographic, cultural, and labor statistics, without including personally identifiable information. ### Source excerpt 高品質で多様なトレーニングデータなしに、日本文化を真に理解するAIを構築することはこれまでほぼ不可能でした。これを変えるため、NVIDIAは、日本の人口統計、地理的分布、文化的特性に沿ったペルソナを含む初のオープン合成データセット、Nemotron-Personas-Japan を公開しました。CC BY 4.0 ライセンスのもと提供される本データセットは、機微な個人データに依存することなく日本社会を反映した AI システム構築のための、プライバシー保護と規制対応を両立した基盤を提供します。 NVIDIA のエンタープライズ向け合成データ生成システム、NeMo Data Designer を用いて作成されたNemotron-Personas-Japan は、すでに広く利用されている US Personas データセットの成功を機に日本版として開発されました。本リリースは、各国・地域におけるソブリン AI 開発を支援する合成ペルソナデータセットとデータ構築方法のグローバルコレクションの第一弾です。 ## Welcome the NVIDIA Llama Nemotron Nano VLM to Hugging Face Hub DevFeed: [Welcome the NVIDIA Llama Nemotron Nano VLM to Hugging Face Hub]() Original publisher: [Read original article]() Author: Amanda Saunders; Amala Sanjay Deshmukh; Kateryna Chumachenko; Annie Surla; Karan; Tuomas Rintamaki; Matthieu Le; Yu Yao; Chen Cui; Timo Roman; Zhiding Yu; Mike Ranzinger Published: 2025-06-27T21:09:27Z Content type: release Language: en Sources: [Hugging Face - Blog]() Topics: [vlm](), [llama](), [Nemotron](), [Nvidia](), [hugging face](), [multimodal](), [Benchmark](), [NeMo](), [datasets]() Tags: [benchmark](), [data](), [datasets](), [hugging-face](), [idp](), [llama](), [multimodal](), [nemo](), [nemotron](), [nvidia](), [ocr](), [performance](), [recognition](), [train](), [use-cases](), [vision](), [vlm](), [workflows]() ### AI overview NVIDIA Llama Nemotron Nano VL is an 8B vision-language model for intelligent document processing. Available on Hugging Face, it extracts and interprets text, tables, charts, diagrams, and other information from complex documents. ### Source excerpt NVIDIA Llama Nemotron Nano VL is a state-of-the-art 8B Vision Language Model (VLM) designed for intelligent document processing, offering high accuracy and multimodal understanding. Available on Hugging Face, it excels in extracting and understanding information from complex documents like invoices, receipts, contracts, and more. ## AI in abundance DevFeed: [AI in abundance]() Original publisher: [Read original article]() Published: 2024-09-17T03:00:00Z Content type: release Language: en Sources: [Mistral AI Blog]() Topics: [Artificial Intelligence](), [AI Platform](), [Serverless](), [API](), [Cloud](), [Frontier Model](), [vllm](), [NeMo](), [multimodal]() Tags: [ai](), [api](), [cloud](), [frontier-model](), [multimodal](), [nemo](), [platform](), [pricing](), [prototyping](), [serverless](), [vision](), [vllm]() ### AI overview Mistral announces a free tier for La Plateforme, broad price reductions, an updated Mistral Small v24.09 model, and free vision capabilities on le Chat with Pixtral 12B. The platform supports tuning and deploying Mistral models as API endpoints, while the updated model targets tasks such as translation, summarization, sentiment analysis, and code-related use cases. ### Source excerpt The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models. ## Announcing Pixtral 12B DevFeed: [Announcing Pixtral 12B]() Original publisher: [Read original article]() Published: 2024-09-17T02:00:00Z Content type: news Language: en Sources: [Mistral AI Blog]() Topics: [Artificial Intelligence](), [multimodal](), [Benchmark](), [NeMo](), [Open Source](), [Claude](), [coding]() Tags: [ai](), [apache](), [benchmark](), [benchmarks](), [claude](), [coding](), [context-window](), [evaluation](), [long-context](), [math](), [models](), [multimodal](), [open-source](), [performance](), [vision]() ### AI overview Mistral AI announces Pixtral 12B, an open-source multimodal model trained on interleaved image and text data. It combines a new 400M-parameter vision encoder with a 12B-parameter decoder based on Mistral Nemo, supports variable image sizes and multiple images in a 128K-token context window, and is released under the Apache 2.0 license. The article reports strong multimodal reasoning and instruction-following performance while maintaining text, coding, and math capabilities. ### Source excerpt Pixtral 12B is deprecated. Discover Mistral AI's latest vision models and capabilities in our updated documentation. ## We're Cutting L40S Prices In Half DevFeed: [We're Cutting L40S Prices In Half]() Original publisher: [Read original article]() Published: 2024-08-15T00:00:00Z Content type: news Language: en Sources: [The Fly Blog]() Topics: [fly.io](), [GPU](), [fly](), [Inference](), [Cloud](), [Artificial Intelligence](), [Generative AI](), [NeMo](), [Nvidia](), [stable-diffusion](), [NVLink]() Tags: [ai](), [cdn](), [close-to-users](), [cloud](), [deploy-app-servers](), [docker](), [elixir](), [fly](), [fly-io](), [generative-ai](), [gpu](), [hardware](), [heroku-alternative](), [heroku-competitor](), [hosting](), [i](), [inference](), [nemo](), [networking](), [nvidia](), [nvlink](), [postgresql-clusters](), [servers](), [stable-diffusion]() ### AI overview Fly.io announces that it has cut the price of NVIDIA L40S GPUs to $1.25 per hour. The article explains that customers most often choose the less powerful A10 for inference and mid-sized generative AI workloads such as Mistral Nemo and Stable Diffusion, while Fly.io's earlier GPU strategy focused on more demanding ideas involving A100 partitioning, NVLink clusters, and training. ### Source excerpt We're Fly.io, a new public cloud with simple, developer-friendly ergonomics. And as of today, cheaper GPUs. Try it out; you'll be deployed in just minutes. We just lowered the prices on NVIDIA L40s GPUs to $1.25 per hour. Why? Because our feet are cold and we burn processor cycles for heat. But also other reasons. Let's back up. We offer 4 different NVIDIA GPU models; in increasing order of performance, they're the A10, the L40S, the 40G PCI A100, and the 80G SXM A100. Guess which one is most popular. We guessed wrong, and spent a lot of time working out how to maximize the amount of GPU power we could deliver to a single Fly Machine. Users surprised us. By a wide margin, the most popular GPU in our inventory is the A10. The A10 is an older generation of NVIDIA GPU with fewer, slower cores and less memory. It's the least capable GPU we offer. But that doesn't matter, because it's capable enough. It's solid for random inference tasks, and handles mid-sized generative AI stuff like Mistral Nemo or Stable Diffusion. For those workloads, there's not that much benefit in getting a beefier GPU. As a result, we can't get new A10s in fast enough for our users. If there's one thing we've learned by talking to our customers over the last 4 years, it's that y'all love a peek behind the curtain. So we're going to let you in on a little secret about how a hardware provider like Fly.io formulates GPU strategy: none of us know what the hell we're doing. If you had asked us in 2023 what the biggest GPU problem we could solve was, we'd have said "selling fractional A100 slices". We burned a whole quarter trying to get MIG, or at least vGPUs, working through IOMMU PCI passthrough on Fly Machines, in a project so cursed that Thomas has forsworn ever programming again. Then we went to market selling whole A100s, and for several more months it looked like the biggest problem we needed to solve was finding a secure way to expose NVLink-ganged A100 clusters to VMs so users could run train ## Mistral NeMo DevFeed: [Mistral NeMo]() Original publisher: [Read original article]() Published: 2024-07-18T08:00:00Z Content type: release Language: en Sources: [Mistral AI Blog]() Topics: [NeMo](), [AI Models](), [long-context](), [Compression](), [Fine-tuning](), [Open Source]() Tags: [compression](), [context-window](), [fine-tuning](), [function-calling](), [models](), [nemo](), [open-source](), [tokens]() ### AI overview Mistral NeMo is a 12B multilingual model developed with NVIDIA, offering a 128k-token context window, strong reasoning and coding performance, function calling, and Apache 2.0 licensing. The release highlights its efficient Tekken tokenizer, FP8 inference, instruction fine-tuning, and comparisons with Gemma 2 9B and Llama 3 8B. ### Source excerpt The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.