# moe Mixture of Experts (MoE) is a neural-network architecture that uses a gating network to select expert subnetworks for each input. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Cohere's new translation model is open weights -- but not for commercial use DevFeed: [Cohere's new translation model is open weights -- but not for commercial use]() Original publisher: [Read original article]() Author: Meredith Shubel Published: 2026-09-11T17:50:11Z Content type: news Language: en Sources: [The New Stack]() Topics: [Inference](), [moe]() Tags: [ai](), [ai-infrastructure](), [ai-models](), [ai-strategy](), [api](), [cohere](), [hugging-face](), [inference](), [mixture-of-experts](), [model](), [models](), [open](), [production](), [release]() ### AI overview Cohere released North Small Translate 1.0 as open weights under CC BY-NC 4.0, allowing download, evaluation, and study but requiring a commercial agreement for production use. Commercial deployment requires a license and use of Cohere's managed Model Vault platform. ### Source excerpt This week, Cohere released North Small Translate 1.0 under a CC BY-NC 4.0 license: the weights are there to download, The post Cohere's new translation model is open weights -- but not for commercial use appeared first on The New Stack. ## How XPUs Meet a World-Class AI Factory DevFeed: [How XPUs Meet a World-Class AI Factory]() Original publisher: [Read original article]() Author: Jesse Clayton Published: 2026-08-24T15:00:54Z Content type: article Language: en Sources: [NVIDIA Blog]() Topics: [AI Factory](), [NVLink](), [AI Infrastructure](), [Network](), [networking](), [Low Latency](), [moe](), [Artificial Intelligence](), [Nvidia](), [AI Platform](), [Latency]() Tags: [agentic-ai](), [ai-factory](), [ai-infrastructure](), [ecosystem](), [ethernet](), [gb300-nvl72](), [hardware](), [mixture-of-experts](), [networking](), [nvidia-dsx](), [nvl72](), [nvlink](), [software](), [time](), [xpu]() ### AI overview The article explains how NVLink Fusion combines custom XPUs with NVIDIA's established AI infrastructure to help build semi-custom AI factories. It focuses on scale-up networking, performance, resiliency, telemetry, platform maturity, and the economics of large-scale AI workloads. ### Source excerpt To generate intelligence at scale, AI factories run continuously, and their economics are defined by delivered output: tokens per second, tokens per watt, cost per token, utilization and uptime. That requires AI infrastructure designed and built as a full factory, not a collection of individual accelerators. Hyperscalers and AI-native companies building custom XPUs must consider [...] ## Hot Chips 2026: Applying High Bandwidth Flash (HBF) DevFeed: [Hot Chips 2026: Applying High Bandwidth Flash (HBF)]() Original publisher: [Read original article]() Author: Chester Lam Published: 2026-08-23T22:51:05Z Content type: article Language: en Sources: [Chips and Cheese]() Topics: [Machine Learning & Artificial Intelligence](), [Inference](), [vllm](), [moe](), [Cache]() Tags: [2026](), [dram](), [machine-learning](), [memory](), [moe](), [ssd](), [vllm]() ### AI overview This article examines how High Bandwidth Flash (HBF) could support machine learning workloads. HBF does not yet have products; the discussion uses simulations and projections to explore software strategies, including moving Mixture-of-Experts components or KV cache data between HBF and faster memory, with vLLM as an example. ### Source excerpt Machine learning workloads have an insatiable appetite for DRAM capacity. Flash memory is cheaper per gigabyte of capacity than DRAM. Could it offer a way out? ## Ling 3.0 Tiny is now available on AI Gateway DevFeed: [Ling 3.0 Tiny is now available on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-08-06T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Artificial Intelligence](), [moe](), [vercel ai sdk](), [long-context](), [SDKs]() Tags: [ai](), [ai-gateway](), [api](), [caching](), [coding-agents](), [context-window](), [cost](), [models](), [moe](), [sdk]() ### AI overview Ling 3.0 Tiny from ANT Group is available on Vercel AI Gateway, initially in a free slot. It is a Mixture-of-Experts model with 7.9B total parameters, approximately 1.3B active parameters per token, a 256K-token context window, and support for up to 32K output tokens. The article also explains how to use it through the AI SDK, the model playground, and coding agents. ### Source excerpt Ling 3.0 Tiny from ANT Group is now on AI Gateway, free to use till 8:00am PT on 8/14. Ling 3.0 Tiny takes the free slot from Ling 3.0 Flash. Ling 3.0 Tiny is a MOE model with 7.9B total parameters and about 1.3B active per token, a 256K token context window, and up to 32K output tokens. The model is built for responsive agents, instruction following, and multi-turn conversation, with native function calling and prompt caching. To use Ling 3.0 Tiny, set model to inclusionai/ling-3.0-tiny-free in the AI SDK. On August 14th, the new model name will be inclusionai/ling-3.0-tiny. Try Ling 3.0 Tiny in the model playground. To use it in a coding agent, run vercel ai-gateway coding-agents setup and select inclusionai/ling-3.0-tiny-free inside the agent. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. Read more ## 34 Amazon Research Awards Build on Trainium recipients announced DevFeed: [34 Amazon Research Awards Build on Trainium recipients announced]() Original publisher: [Read original article]() Author: Amazon Research Awards team Published: 2026-08-05T15:00:00Z Content type: news Language: en Sources: [Amazon Science homepage]() Topics: [Artificial Intelligence](), [responsible-ai](), [AWS AI chips](), [AI Research](), [Optimization](), [Inference](), [moe](), [Large Language Model](), [distributed-systems](), [synthetic-data]() Tags: [academic-ai-funding](), [ai](), [ai-research](), [ai-research-grants](), [ai-safety-and-alignment](), [amazon-research-awards](), [ara](), [aws-ai-chips](), [aws-trainium](), [build-on-trainium](), [data](), [deep-learning](), [distributed-systems](), [inference](), [internal-ara-program-updates](), [llm](), [machine-learning-research](), [mixture-of-experts](), [optimization](), [research](), [responsible-ai](), [synthetic](), [synthetic-data-generation]() ### AI overview Amazon announces 34 recipients of its Build on Trainium program, a $110 million credit initiative supporting AI research and university education. The awards fund work in areas including Responsible AI, language models, synthetic data, distributed systems, model architectures, libraries, and optimization on AWS Trainium. ### Source excerpt Amazon announces 34 recipients of the Build on Trainium program, a $110 million credit initiative supporting AI research at 30 universities including Stanford, UC Berkeley, UIUC, UCLA, CMU, and MIT, with a focus on Responsible AI. ## Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents DevFeed: [Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents]() Original publisher: [Read original article]() Author: Tuomas Rintamaki; Amala Sanjay Deshmukh; Nabin Mulepati; Collin McCarthy; Pritam Biswas; Arushi Goel; Alexandre Milesi; Danial Mohseni Taheri; Kateryna Chumachenko; Isabel Hulseman; Zhehuai Chen; Kara Published: 2026-04-28T15:58:57Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [multimodal](), [Nemotron](), [long-context](), [asr](), [computer-use](), [Mamba](), [model architecture](), [moe](), [Transformer](), [Nvidia](), [Reinforcement learning](), [NVFP4]() Tags: [alternatives](), [analysis](), [architecture](), [benchmarks](), [computer-use](), [efficiency](), [long-context](), [models](), [multimodal](), [nemotron](), [nvidia](), [optimization](), [reasoning](), [reinforcement-learning](), [speed]() ### AI overview NVIDIA introduces Nemotron 3 Nano Omni, an omni-modal model for document analysis, image reasoning, speech recognition, long audio-video understanding, computer use, and general reasoning. It combines a hybrid Mamba-Transformer Mixture-of-Experts backbone with vision and audio encoders, supports long multimodal contexts, and reports strong benchmark accuracy, throughput, reasoning speed, and system efficiency. ### Source excerpt Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents - NVIDIA Nemotron 3 Nano Omni is a new omni-modal understanding model built for real-world document analysis, multiple image reasoning, automatic speech recognition, long audio-video understanding, agentic computer use, and general reasoning. - It extends the Nemotron multimodal line from a strong vision-language system to a broader text + image + video + audio model. ## Technical Deep Dive: How DigitalOcean and AMD Delivered a 2x Production Inference Performance Increase for Character.ai DevFeed: [Technical Deep Dive: How DigitalOcean and AMD Delivered a 2x Production Inference Performance Increase for Character.ai]() Original publisher: [Read original article]() Author: Karnik Modi Published: 2026-01-13T12:30:00Z Content type: article Language: en Sources: [DigitalOcean]() Topics: [Artificial Intelligence](), [Digital Ocean](), [GPU](), [Inference](), [Inference Performance](), [GPU optimization](), [moe](), [Kubernetes](), [model-deployment](), [PyTorch](), [qwen]() Tags: [ai](), [digitalocean](), [engineering](), [gpu](), [inference](), [inference-performance](), [infrastructure](), [kubernetes](), [mixture-of-experts](), [news](), [performance](), [platforms](), [qwen](), [technical]() ### AI overview This technical deep dive describes how Character.ai, AMD, and DigitalOcean optimized inference for the Qwen3-235B Instruct FP8 model on AMD Instinct MI300X and MI325X GPUs. The reported optimizations, including parallelization, FP8 execution paths, optimized kernels, topology-aware allocation, and Kubernetes orchestration, produced up to a 2x improvement in production request throughput under stated latency and concurrency constraints. ### Source excerpt Background: How Character.ai worked with DigitalOcean and AMD to optimize performance Character.ai, a leading AI entertainment platform with about 20 million worldwide users, wanted to optimize GPU performance and achieve lower inference costs for its application, which requires low-latency performance at large scale. They approached DigitalOcean and AMD in order to achieve this goal. Working closely together, the Character.ai, AMD, and DigitalOcean teams optimized AMD Instinct™ MI300X and MI325X GPU platforms, resulting in a 2x production inference throughput. In optimized configurations, DigitalOcean delivered high request density per node while maintaining exceptional p90 responsiveness for initial token and sustained token generation throughput, outperforming prior deployments on generic, non-optimized GPU infrastructure. These gains were achieved through platform-level optimizations, including clever parallelization strategies for large Mixture-of-Experts models, efficient FP8 execution paths, optimized kernels with AITER, topology-aware GPU allocation, and production-ready Kubernetes orchestration through DigitalOcean Kubernetes (DOKS). Together, these capabilities allowed Character.ai to scale inference predictably without increasing operational burden. In this post, we will explore the specific orchestration and tuning strategies that made these gains possible. Technical deep dive overview Character.ai leverages multiple models like Qwen, Mistral and more to power their applications. This document is focused on how we optimized the Qwen3-235B Instruct FP8 model on a cluster of DigitalOcean featuring AMD Instinct GPUs. This workload was migrated from a generic, non-optimized setup on other providers to AMD Instinct™ MI325X platform on DigitalOcean, and following the outlined optimizations we were able to achieve up to a 2x improvement in request throughput (QPS) under strict latency and concurrency constraints. The Character.ai team has a demanding workload, ## Google Cloud C4 Brings a 70% TCO improvement on GPT OSS with Intel and Hugging Face DevFeed: [Google Cloud C4 Brings a 70% TCO improvement on GPT OSS with Intel and Hugging Face]() Original publisher: [Read original article]() Author: Jiqing.Feng; Matrix Yao; Ke Ding; Ilyas Moutawwakil Published: 2025-10-16T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [moe](), [cpu](), [AI, ML & Data Engineering]() Tags: [cpu](), [google-cloud](), [gpt-oss](), [hugging-face](), [inference](), [intel](), [llm](), [mixture-of-experts-moe](), [open-source](), [performance]() ### AI overview The article benchmarks GPT OSS mixture-of-experts text generation on Google Cloud Intel Xeon virtual machines. It describes an expert-execution optimization and reports throughput, latency, and total-cost-of-ownership comparisons between Xeon generations. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Welcome GPT OSS, the new open-source model family from OpenAI! DevFeed: [Welcome GPT OSS, the new open-source model family from OpenAI!]() Original publisher: [Read original article]() Author: Vaibhav Srivastav; Pedro Cuenca; Lewis Tunstall; Clem 🤗; Matthew Carrigan; Clémentine Fourrier; Célina Hanouti; Lucain Pouget; Marc Sun; Simon Pagezy Published: 2025-08-05T00:00:00Z Content type: release Language: en Sources: [Hugging Face - Blog]() Topics: [gpt-oss](), [Open Source](), [OpenAI](), [Artificial Intelligence](), [inference-providers](), [llama.cpp](), [moe](), [Ollama](), [Python](), [quantization](), [Transformers](), [vllm]() Tags: [api](), [artificial-intelligence](), [community](), [gpt](), [gpt-oss](), [inference-providers](), [javascript](), [llama-cpp](), [llm](), [moe](), [ollama](), [open-source](), [openai](), [python](), [quantization](), [transformers](), [vllm]() ### AI overview Hugging Face welcomes OpenAI's gpt-oss open-source model family. The article describes the models' Apache 2.0 licensing, local deployment options, reasoning and tool-use capabilities, MoE architecture, quantization, supported inference implementations, and access through Inference Providers and the Responses API. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## DeepSeek's reported efficiency and Nvidia's stock decline DevFeed: [DeepSeek's reported efficiency and Nvidia's stock decline]() Original publisher: [Read original article]() Author: redmadrobot (red\_mad\_robot) Published: 2025-01-28T16:53:47Z Content type: opinion Language: ru Sources: [Redmadrobot EN](), [Redmadrobot RU]() Topics: [deepseek](), [Nvidia](), [Artificial Intelligence](), [GPU](), [moe](), [grpo](), [ChatGPT]() Tags: [ai](), [chatgpt](), [deepseek](), [gpu](), [grpo](), [moe](), [nvidia](), [openai](), [tag-13e2af703774](), [tag-61cd5a476b1d]() ### AI overview The article argues that DeepSeek's reported lower training and inference costs contributed to concern about Nvidia's GPU-demand business model and coincided with a sharp Nvidia stock decline. It attributes the claimed efficiency to reinforcement learning with GRPO and a Mixture of Experts architecture. ### Source excerpt Акции NVIDIA рухнули, потеряв за одну ночь $600 миллиардов рыночной капитализации -- крупнейший дневной обвал на рынке ценных бумаг в истории США. Это событие стало шоком для рынка GPU, будущее которого, как казалось, предопределено на годы вперед. Причиной стал запуск китайской нейросети DeepSeek, которая не только превзошла западных конкурентов, таких как ChatGPT, но и стоила в разработке в тысячу раз дешевле. Этот прорыв поставил под угрозу бизнес-модель NVIDIA, основанную на стабильном спросе на их GPU. Разбираемся, как так вышло, вместе с Валерой Ковальским, CEO NDT by red_mad_robot. Читать далее ## Open-R1: a fully open reproduction of DeepSeek-R1 DevFeed: [Open-R1: a fully open reproduction of DeepSeek-R1]() Original publisher: [Read original article]() Author: Elie Bakouch; Leandro von Werra; Lewis Tunstall Published: 2025-01-28T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [deepseek](), [Open Source](), [Reinforcement learning](), [Large Language Model](), [moe](), [Training AI Models](), [Chinchilla scaling law](), [datasets](), [AI Development]() Tags: [artificial-intelligence](), [datasets](), [deepseek](), [llms](), [mixture-of-experts-moe](), [open-source](), [reasoning](), [reinforcement-learning](), [research](), [scaling-laws](), [training]() ### AI overview The article introduces Open-R1, an open-source project to reproduce and extend DeepSeek-R1's reasoning-model training pipeline. It discusses reinforcement learning, reasoning-specific datasets, training-code transparency, scaling laws, and the DeepSeek-V3 Mixture of Experts foundation model. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Cheaper, Better, Faster, Stronger DevFeed: [Cheaper, Better, Faster, Stronger]() Original publisher: [Read original article]() Published: 2024-04-17T14:00:00Z Content type: release Language: en Sources: [Mistral AI Blog]() Topics: [mixtral](), [moe](), [Large Language Model](), [Open Source](), [Open Source Models & Datasets](), [coding](), [Fine-tuning](), [long-context](), [Inference](), [Application Development]() Tags: [ai](), [coding](), [context-window](), [fine-tuning](), [inference](), [llm](), [mixtral](), [mixture-of-experts](), [models](), [open](), [open-source](), [performance]() ### AI overview Mistral introduces Mixtral 8x22B, an open sparse Mixture-of-Experts model with 141B total parameters and 39B active parameters. It emphasizes cost-efficient performance, multilingual capabilities, mathematics and coding, function calling, a 64K-token context window, fine-tuning, and Apache 2.0 licensing. ### Source excerpt The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models. ## Mixtral of experts DevFeed: [Mixtral of experts]() Original publisher: [Read original article]() Published: 2023-12-11T07:00:00Z Content type: release Language: en Sources: [Mistral AI Blog]() Topics: [mixtral](), [moe](), [Artificial Intelligence](), [Code generation](), [Inference](), [Latency](), [llama](), [data]() Tags: [ai](), [apache](), [architectures](), [benchmarks](), [code](), [code-generation](), [inference](), [latency](), [llama](), [mixtral](), [mixture-of-experts](), [models](), [open](), [release]() ### AI overview Mistral AI releases Mixtral 8x7B, an open-weight sparse mixture-of-experts model licensed under Apache 2.0. The article reports strong benchmark results, faster inference, efficient cost and latency characteristics, multilingual support, and strong code-generation performance. ### Source excerpt The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.