# Mixture of Experts (MoE)

Published articles for Mixture of Experts (MoE).

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Translating CUDA Tile Operations from Python to Rust Using Agentic AI

DevFeed: [Translating CUDA Tile Operations from Python to Rust Using Agentic AI](<https://devfeed.tech/articles/translating-cuda-tile-operations-from-python-to-rust-using-agentic-ai-31486.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/translating-cuda-tile-operations-from-python-to-rust-using-agentic-ai/>)

Author: Tanya Lenz

Published: 2026-09-16T16:28:59Z

Content type: tutorial

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [CUDA Tile](<https://devfeed.tech/topics/cuda-tile.md>), [Rust](<https://devfeed.tech/topics/rust.md>), [Agent Skill](<https://devfeed.tech/topics/agent-skill.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [benchmarking](<https://devfeed.tech/topics/benchmarking.md>), [Compiler](<https://devfeed.tech/topics/compiler.md>)

Tags: [agent-skill](<https://devfeed.tech/tags/agent-skill.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [cuda-tile](<https://devfeed.tech/tags/cuda-tile.md>), [cutile](<https://devfeed.tech/tags/cutile.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [python](<https://devfeed.tech/tags/python.md>), [rust](<https://devfeed.tech/tags/rust.md>)

### AI overview

This NVIDIA developer article explains a multi-agent workflow for translating cuTile Python and Triton-TileIR GPU kernels into cuTile Rust. The team ported 24 public TileGym operators, covering about 40 kernels, and achieved 99.5% of cuTile Python performance on average, with correctness and performance checks at each stage.

### Source excerpt

cuTile Rust (cutile-rs) is a tile-based system for safe, idiomatic GPU kernel authoring in the Rust programming language. Extending the Rust ownership model to...

## Dense vs. MoE Models: Active Parameters, Throughput, and When to Choose Each

DevFeed: [Dense vs. MoE Models: Active Parameters, Throughput, and When to Choose Each](<https://devfeed.tech/articles/dense-vs-moe-models-active-parameters-throughput-and-when-to-choose-each-26912.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/dense-vs-moe-models-active-parameters-throughput-and-when-to-choose-each/>)

Author: Elizabeth Goodman

Published: 2026-09-15T17:00:11Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [Nemotron](<https://devfeed.tech/topics/nemotron.md>), [Routing (disambiguation)](<https://devfeed.tech/topics/routing.md>)

Tags: [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [cost](<https://devfeed.tech/tags/cost.md>), [data-center-cloud](<https://devfeed.tech/tags/data-center-cloud.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [llms](<https://devfeed.tech/tags/llms.md>), [memory](<https://devfeed.tech/tags/memory.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [models](<https://devfeed.tech/tags/models.md>), [moe](<https://devfeed.tech/tags/moe.md>), [nemo](<https://devfeed.tech/tags/nemo.md>), [nemotron](<https://devfeed.tech/tags/nemotron.md>), [performance](<https://devfeed.tech/tags/performance.md>), [router](<https://devfeed.tech/tags/router.md>), [routing](<https://devfeed.tech/tags/routing.md>), [tokens](<https://devfeed.tech/tags/tokens.md>)

### AI overview

This article explains how dense and Mixture-of-Experts models activate parameters, compares their effects on throughput, memory cost, and serving complexity, and discusses when each architecture fits different deployment constraints. It uses Nemotron 3.5 Lightning as an example of an MoE model.

### Source excerpt

How can a 30B-parameter model activate only 3B parameters per token, and still use the capacity of the larger model? Nemotron 3.5 Lightning illustrates the...

## Accelerating Dropless MoE Training in JAX with NVIDIA Transformer Engine

DevFeed: [Accelerating Dropless MoE Training in JAX with NVIDIA Transformer Engine](<https://devfeed.tech/articles/accelerating-dropless-moe-training-in-jax-with-nvidia-transformer-engine-21079.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/accelerating-dropless-moe-training-in-jax-with-nvidia-transformer-engine/>)

Author: Tanya Lenz

Published: 2026-09-14T16:39:15Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [Routing (disambiguation)](<https://devfeed.tech/topics/routing.md>), [GB200](<https://devfeed.tech/topics/gb200.md>), [Network](<https://devfeed.tech/topics/network.md>), [Python](<https://devfeed.tech/topics/python.md>), [deepseek](<https://devfeed.tech/topics/deepseek.md>), [mixtral](<https://devfeed.tech/topics/mixtral.md>), [qwen](<https://devfeed.tech/topics/qwen.md>)

Tags: [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [communication](<https://devfeed.tech/tags/communication.md>), [deepseek](<https://devfeed.tech/tags/deepseek.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [gb200](<https://devfeed.tech/tags/gb200.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [mixtral](<https://devfeed.tech/tags/mixtral.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [mlops](<https://devfeed.tech/tags/mlops.md>), [moe](<https://devfeed.tech/tags/moe.md>), [networks](<https://devfeed.tech/tags/networks.md>), [nvfp4](<https://devfeed.tech/tags/nvfp4.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [performance](<https://devfeed.tech/tags/performance.md>), [python](<https://devfeed.tech/tags/python.md>), [qwen](<https://devfeed.tech/tags/qwen.md>), [router](<https://devfeed.tech/tags/router.md>), [routing](<https://devfeed.tech/tags/routing.md>), [tensors](<https://devfeed.tech/tags/tensors.md>), [token](<https://devfeed.tech/tags/token.md>), [tokens](<https://devfeed.tech/tags/tokens.md>), [training-ai-models](<https://devfeed.tech/tags/training-ai-models.md>)

### AI overview

This article explains how NVIDIA Transformer Engine and JAX kernel optimizations accelerate dropless Mixture of Experts (MoE) training. It describes bottlenecks from token routing, expert dispatch and gathering, all-to-all communication, and ragged expert matrix operations. In DeepSeek-V3 training on NVIDIA GB200, the optimized approach increased performance from 103 to 1,068 TFLOPS per GPU, a 10.4x improvement.

### Source excerpt

Mixture of experts (MoE) has become one of the defining architectural trends in large-scale AI model training. DeepSeek, Qwen, and Mixtral are examples of MoE...

## "Machine translation is still broken for most of the world's languages": Cohere builds non-reasoning for a reason

DevFeed: ["Machine translation is still broken for most of the world's languages": Cohere builds non-reasoning for a reason](<https://devfeed.tech/articles/machine-translation-is-still-broken-for-most-of-the-world-s-languages-cohere-builds-non-reasoning-for-a-reason-10829.md>)

Original publisher: [Read original article](<https://thenewstack.io/cohere-north-translate-sovereignty/>)

Author: Adrian Bridgwater

Published: 2026-09-13T14:21:46Z

Content type: news

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [cohere](<https://devfeed.tech/topics/cohere.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [qwen](<https://devfeed.tech/topics/qwen.md>), [gemma4](<https://devfeed.tech/topics/gemma4.md>), [Google](<https://devfeed.tech/topics/google.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [aya](<https://devfeed.tech/tags/aya.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cohere](<https://devfeed.tech/tags/cohere.md>), [gemma](<https://devfeed.tech/tags/gemma.md>), [google](<https://devfeed.tech/tags/google.md>), [inference](<https://devfeed.tech/tags/inference.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [model](<https://devfeed.tech/tags/model.md>), [open](<https://devfeed.tech/tags/open.md>), [qwen](<https://devfeed.tech/tags/qwen.md>)

### AI overview

Cohere's North Small Translate is an open-weight mixture-of-experts machine translation model covering 50 languages. The article discusses its non-reasoning design, sovereign AI positioning, deployment options, efficiency claims, and reported WMT26 benchmark comparisons.

### Source excerpt

Enterprise AI company Cohere announced North Small Translate last week, a mixture-of-experts (MOE) open-weight machine translation model that works across The post "Machine translation is still broken for most of the world's languages": Cohere builds non-reasoning for a reason appeared first on The New Stack.

## When to Use Encode-Prefill-Decode Disaggregation to Accelerate Multimodal Model Serving

DevFeed: [When to Use Encode-Prefill-Decode Disaggregation to Accelerate Multimodal Model Serving](<https://devfeed.tech/articles/when-to-use-encode-prefill-decode-disaggregation-to-accelerate-multimodal-model-serving-6945.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/when-to-use-encode-prefill-decode-disaggregation-to-accelerate-multimodal-model-serving/>)

Author: Tanya Lenz

Published: 2026-09-09T20:31:04Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [Optimization](<https://devfeed.tech/topics/optimization.md>), [model-deployment](<https://devfeed.tech/topics/model-deployment.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>), [Dynamo](<https://devfeed.tech/topics/dynamo.md>), [Inference Performance](<https://devfeed.tech/topics/inference-performance.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [computer-vision-video-analytics](<https://devfeed.tech/tags/computer-vision-video-analytics.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [dynamo](<https://devfeed.tech/tags/dynamo.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [inference](<https://devfeed.tech/tags/inference.md>), [low-latency-inference](<https://devfeed.tech/tags/low-latency-inference.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [model-serving](<https://devfeed.tech/tags/model-serving.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [nvfp4](<https://devfeed.tech/tags/nvfp4.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [optimization](<https://devfeed.tech/tags/optimization.md>)

### AI overview

This article explains when encode-prefill-decode disaggregation improves multimodal model serving. Using NVIDIA Dynamo, it separates vision encoding from LLM prefill and decode so the stages can batch, schedule, and scale independently. The approach is most effective for image-heavy prompts, short-to-medium outputs, and quantized mixture-of-experts models, with reported gains of up to 5x in time to first token and 7x in end-to-end response time.

### Source excerpt

Encode-prefill-decode (EPD) disaggregation is an inference optimization technique for multimodal models that separates the vision encoder stage from the prefill...

## Frontier Reasoning Reaches the Edge: How to Deploy and Optimize Models on NVIDIA Jetson

DevFeed: [Frontier Reasoning Reaches the Edge: How to Deploy and Optimize Models on NVIDIA Jetson](<https://devfeed.tech/articles/frontier-reasoning-reaches-the-edge-how-to-deploy-and-optimize-models-on-nvidia-jetson-6826.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/frontier-reasoning-reaches-the-edge-how-to-deploy-and-optimize-models-on-nvidia-jetson/>)

Author: Elizabeth Goodman

Published: 2026-09-04T16:21:04Z

Content type: tutorial

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [Jetson](<https://devfeed.tech/topics/jetson.md>), [model-deployment](<https://devfeed.tech/topics/model-deployment.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [Inference Performance](<https://devfeed.tech/topics/inference-performance.md>), [Optimization](<https://devfeed.tech/topics/optimization.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>)

Tags: [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [edge](<https://devfeed.tech/tags/edge.md>), [edge-computing](<https://devfeed.tech/tags/edge-computing.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [inference](<https://devfeed.tech/tags/inference.md>), [inference-performance](<https://devfeed.tech/tags/inference-performance.md>), [jetpack](<https://devfeed.tech/tags/jetpack.md>), [jetson](<https://devfeed.tech/tags/jetson.md>), [jetson-orin](<https://devfeed.tech/tags/jetson-orin.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [nvfp4](<https://devfeed.tech/tags/nvfp4.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [physical-ai](<https://devfeed.tech/tags/physical-ai.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [thor](<https://devfeed.tech/tags/thor.md>), [tutorial](<https://devfeed.tech/tags/tutorial.md>), [vllm](<https://devfeed.tech/tags/vllm.md>)

### AI overview

A tutorial on deploying and optimizing compact reasoning and agentic AI models on NVIDIA Jetson. It covers choosing models, improving inference with NVFP4 quantization and speculative decoding, serving example models with vLLM, and validating a configuration for a workload.

### Source excerpt

Running reasoning and agentic AI at the edge has been harder than it needs to be. Until recently, models capable of multi-step reasoning were too large to run...

## Sparks Fly: NVIDIA Accelerates Local AI at IFA 2026

DevFeed: [Sparks Fly: NVIDIA Accelerates Local AI at IFA 2026](<https://devfeed.tech/articles/sparks-fly-nvidia-accelerates-local-ai-at-ifa-2026-6954.md>)

Original publisher: [Read original article](<https://blogs.nvidia.com/blog/local-ai-ifa-next-gen-agents-nv-pair-rtx-spark/>)

Author: Gerardo Delgado

Published: 2026-09-03T16:00:59Z

Content type: news

Language: en

Sources: [NVIDIA Blog](<https://devfeed.tech/sources/nvidia-blog.md>)

Topics: [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [Hardware](<https://devfeed.tech/topics/hardware.md>), [Inference Performance](<https://devfeed.tech/topics/inference-performance.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [dgx-spark](<https://devfeed.tech/tags/dgx-spark.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [inference](<https://devfeed.tech/tags/inference.md>), [llama-cpp](<https://devfeed.tech/tags/llama-cpp.md>), [local-ai](<https://devfeed.tech/tags/local-ai.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [nvidia-rtx](<https://devfeed.tech/tags/nvidia-rtx.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [rtx-ai-garage](<https://devfeed.tech/tags/rtx-ai-garage.md>), [rtx-spark](<https://devfeed.tech/tags/rtx-spark.md>), [video](<https://devfeed.tech/tags/video.md>), [vllm](<https://devfeed.tech/tags/vllm.md>)

### AI overview

NVIDIA announces local-AI updates at IFA 2026, including agent tooling, faster local inference, RTX Spark Windows PCs, and locally runnable models for agentic, coding, and video-generation workloads.

### Source excerpt

Frontier intelligence is going local. At IFA 2026, NVIDIA, Microsoft and its partners are teaming up to provide faster inference and new tools that make agents easier to set up and run locally on NVIDIA hardware. New compact NVIDIA RTX Spark Windows PCs are also coming in October to give AI enthusiasts, developers and creators [...]

## 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](<https://devfeed.tech/articles/experiment-with-qwen3-8-flash-next-on-nvidia-gb300-nvl72-for-agentic-coding-6819.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/experiment-with-qwen3-8-flash-next-on-nvidia-gb300-nvl72-for-agentic-coding/>)

Author: Michelle Horton

Published: 2026-08-26T17:07:12Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [qwen](<https://devfeed.tech/topics/qwen.md>), [long-context](<https://devfeed.tech/topics/long-context.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>), [NeMo](<https://devfeed.tech/topics/nemo.md>), [sglang](<https://devfeed.tech/topics/sglang.md>), [TensorRT-LLM](<https://devfeed.tech/topics/tensorrt-llm.md>), [vllm](<https://devfeed.tech/topics/vllm.md>), [rust-ai](<https://devfeed.tech/topics/rust-ai.md>)

Tags: [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [gb300-nvl72](<https://devfeed.tech/tags/gb300-nvl72.md>), [inference](<https://devfeed.tech/tags/inference.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [nemo](<https://devfeed.tech/tags/nemo.md>), [nvlink](<https://devfeed.tech/tags/nvlink.md>), [qwen](<https://devfeed.tech/tags/qwen.md>), [sglang](<https://devfeed.tech/tags/sglang.md>), [tensorrt-llm](<https://devfeed.tech/tags/tensorrt-llm.md>), [top-stories](<https://devfeed.tech/tags/top-stories.md>), [vllm](<https://devfeed.tech/tags/vllm.md>)

### 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...

## 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](<https://devfeed.tech/articles/nvidia-vera-rubin-and-blackwell-set-a-new-standard-for-agentic-ai-performance-per-watt-6912.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/nvidia-vera-rubin-and-blackwell-set-a-new-standard-for-agentic-ai-performance-per-watt/>)

Author: Elizabeth Goodman

Published: 2026-08-24T15:00:05Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-factory](<https://devfeed.tech/tags/ai-factory.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [blackwell](<https://devfeed.tech/tags/blackwell.md>), [cache](<https://devfeed.tech/tags/cache.md>), [cloud-networking](<https://devfeed.tech/tags/cloud-networking.md>), [cloud-services](<https://devfeed.tech/tags/cloud-services.md>), [data-center-cloud](<https://devfeed.tech/tags/data-center-cloud.md>), [gb300-nvl72](<https://devfeed.tech/tags/gb300-nvl72.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [inference](<https://devfeed.tech/tags/inference.md>), [long-context](<https://devfeed.tech/tags/long-context.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [nemotron](<https://devfeed.tech/tags/nemotron.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [performance](<https://devfeed.tech/tags/performance.md>), [software-defined-data-center](<https://devfeed.tech/tags/software-defined-data-center.md>), [tools](<https://devfeed.tech/tags/tools.md>), [vera-rubin](<https://devfeed.tech/tags/vera-rubin.md>), [vera-rubin-nvl72](<https://devfeed.tech/tags/vera-rubin-nvl72.md>)

### 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...

## Open-weight models are fast on Neon AI Gateway. Here's why

DevFeed: [Open-weight models are fast on Neon AI Gateway. Here's why](<https://devfeed.tech/articles/open-weight-models-are-fast-on-neon-ai-gateway-here-s-why-5701.md>)

Original publisher: [Read original article](<https://neon.com/blog/open-weight-models-are-fast-on-neon-ai-gateway>)

Author: Carlota Soto

Published: 2026-08-20T12:00:00Z

Content type: article

Language: en

Sources: [Blog -- Neon Docs](<https://devfeed.tech/sources/blog-neon-docs.md>)

Topics: [databricks](<https://devfeed.tech/topics/databricks.md>), [Inference Performance](<https://devfeed.tech/topics/inference-performance.md>), [model-deployment](<https://devfeed.tech/topics/model-deployment.md>), [Low-Latency Inference](<https://devfeed.tech/topics/low-latency-inference.md>), [Caching](<https://devfeed.tech/topics/caching.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [gpt-oss](<https://devfeed.tech/topics/gpt-oss.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [caching](<https://devfeed.tech/tags/caching.md>), [databricks](<https://devfeed.tech/tags/databricks.md>), [gpt-oss](<https://devfeed.tech/tags/gpt-oss.md>), [inference](<https://devfeed.tech/tags/inference.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [performance](<https://devfeed.tech/tags/performance.md>), [product](<https://devfeed.tech/tags/product.md>), [speed](<https://devfeed.tech/tags/speed.md>)

### AI overview

The article explains why open-weight models can deliver low latency on Neon AI Gateway when paired with Databricks Foundation Model APIs and an optimized serving stack. It highlights continuous batching, KV-cache paging, custom kernels, quantization, multi-GPU layouts, prompt caching, and Mixture-of-Experts architectures.

### Source excerpt

Open-weight models are built for performance, but how they're served determines whether end users actually feel that speed. Neon AI Gateway calls Databricks Foundation Model APIs for Databricks-hosted open-weight models, a stack that has years of inference engineering behind it.

## Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300 NVL72

DevFeed: [Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300 NVL72](<https://devfeed.tech/articles/serve-qwen3-8-2-4t-a95b-a-2-4t-parameter-model-with-configurable-reasoning-on-nvidia-gb300-nvl72-6938.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/serve-qwen3-8-2-4t-a95b-a-2-4t-parameter-model-with-configurable-reasoning-on-nvidia-gb300-nvl72/>)

Author: Michelle Horton

Published: 2026-08-12T18:23:13Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [AI Bots](<https://devfeed.tech/topics/ai-bots.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [cache](<https://devfeed.tech/tags/cache.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [featured](<https://devfeed.tech/tags/featured.md>), [gb300-nvl72](<https://devfeed.tech/tags/gb300-nvl72.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [inference](<https://devfeed.tech/tags/inference.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [model](<https://devfeed.tech/tags/model.md>), [nvfp4](<https://devfeed.tech/tags/nvfp4.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [performance](<https://devfeed.tech/tags/performance.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [routing](<https://devfeed.tech/tags/routing.md>), [top-stories](<https://devfeed.tech/tags/top-stories.md>)

### AI overview

The article describes serving Alibaba's open-weight Qwen3.8-2.4T-A95B model on NVIDIA GB300 NVL72 systems for large-scale reasoning and agentic workloads.

### Source excerpt

Alibaba released the open weights for Qwen3.8-2.4T-A95B (Qwen3.8-Max), its largest open-weight model, bringing near-frontier capabilities to the open...

## NVIDIA Nemotron 3.5 Lightning Delivers Fast, Accurate Specialized Task Execution for Long-Running Agents

DevFeed: [NVIDIA Nemotron 3.5 Lightning Delivers Fast, Accurate Specialized Task Execution for Long-Running Agents](<https://devfeed.tech/articles/nvidia-nemotron-3-5-lightning-delivers-fast-accurate-specialized-task-execution-for-long-running-agents-6899.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/nvidia-nemotron-3-5-lightning-delivers-fast-accurate-specialized-task-execution-for-long-running-agents/>)

Author: Tanya Lenz

Published: 2026-08-11T13:01:07Z

Content type: release

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [Language models](<https://devfeed.tech/topics/language-models.md>), [AI Bots](<https://devfeed.tech/topics/ai-bots.md>)

Tags: [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [dgx-spark](<https://devfeed.tech/tags/dgx-spark.md>), [featured](<https://devfeed.tech/tags/featured.md>), [inference](<https://devfeed.tech/tags/inference.md>), [low-latency](<https://devfeed.tech/tags/low-latency.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [nemoclaw](<https://devfeed.tech/tags/nemoclaw.md>), [nemotron](<https://devfeed.tech/tags/nemotron.md>), [nvfp4](<https://devfeed.tech/tags/nvfp4.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [routing](<https://devfeed.tech/tags/routing.md>), [top-stories](<https://devfeed.tech/tags/top-stories.md>)

### AI overview

NVIDIA introduces Nemotron 3.5 Lightning, an open 30B MoE model with 3B active parameters for fast, high-volume execution in long-running AI agents. It also presents NeMo Switchyard for routing tasks to appropriate models.

### Source excerpt

Long-running AI agents spend most of their time on high-volume execution: tool calls, result validation, and subagent delegation. Using a frontier reasoning...

## Setting a World Record for MoE Pre-Training on NVIDIA GB300 NVL72

DevFeed: [Setting a World Record for MoE Pre-Training on NVIDIA GB300 NVL72](<https://devfeed.tech/articles/setting-a-world-record-for-moe-pre-training-on-nvidia-gb300-nvl72-6939.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/setting-a-world-record-for-moe-pre-training-on-nvidia-gb300-nvl72/>)

Author: Kirthi Devleker

Published: 2026-07-21T18:30:00Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [AI Platform](<https://devfeed.tech/topics/ai-platform.md>), [NCCL](<https://devfeed.tech/topics/nccl.md>), [networking](<https://devfeed.tech/topics/networking.md>), [deepseek](<https://devfeed.tech/topics/deepseek.md>)

Tags: [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-platform](<https://devfeed.tech/tags/ai-platform.md>), [ai-training](<https://devfeed.tech/tags/ai-training.md>), [collective](<https://devfeed.tech/tags/collective.md>), [communication](<https://devfeed.tech/tags/communication.md>), [compute](<https://devfeed.tech/tags/compute.md>), [data-center-cloud](<https://devfeed.tech/tags/data-center-cloud.md>), [deepseek](<https://devfeed.tech/tags/deepseek.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [featured](<https://devfeed.tech/tags/featured.md>), [frontier-model](<https://devfeed.tech/tags/frontier-model.md>), [gb300-nvl72](<https://devfeed.tech/tags/gb300-nvl72.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm-techniques](<https://devfeed.tech/tags/llm-techniques.md>), [low-latency](<https://devfeed.tech/tags/low-latency.md>), [megatron](<https://devfeed.tech/tags/megatron.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [moe](<https://devfeed.tech/tags/moe.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [nvl72](<https://devfeed.tech/tags/nvl72.md>), [performance](<https://devfeed.tech/tags/performance.md>), [top-stories](<https://devfeed.tech/tags/top-stories.md>), [train](<https://devfeed.tech/tags/train.md>), [training-ai-models](<https://devfeed.tech/tags/training-ai-models.md>)

### AI overview

The article explains how NVIDIA GB300 NVL72 achieved a world record for DeepSeek-V3 671B mixture-of-experts pre-training. It focuses on the communication demands of MoE models, including all-to-all traffic between GPUs, and the need for tightly coupled scale-up and predictable scale-out networking to sustain delivered training performance.

### Source excerpt

Frontier model pre-training has converged on mixture of experts (MoE), which is fundamentally changing what limits large-scale AI training. As compute per token...

## Inside NVIDIA Rubin GPU Architecture: Powering the Era of Agentic AI

DevFeed: [Inside NVIDIA Rubin GPU Architecture: Powering the Era of Agentic AI](<https://devfeed.tech/articles/inside-nvidia-rubin-gpu-architecture-powering-the-era-of-agentic-ai-6863.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/inside-nvidia-rubin-gpu-architecture-powering-the-era-of-agentic-ai/>)

Author: Eduardo Alvarez

Published: 2026-07-21T18:15:00Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [GPU](<https://devfeed.tech/topics/gpu.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [Inference Performance](<https://devfeed.tech/topics/inference-performance.md>), [long-context](<https://devfeed.tech/topics/long-context.md>), [datacenter](<https://devfeed.tech/topics/datacenter.md>), [Transformer](<https://devfeed.tech/topics/transformer.md>), [Deployment](<https://devfeed.tech/topics/deployment.md>)

Tags: [accelerate](<https://devfeed.tech/tags/accelerate.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-factory](<https://devfeed.tech/tags/ai-factory.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [blackwell](<https://devfeed.tech/tags/blackwell.md>), [cache](<https://devfeed.tech/tags/cache.md>), [compute](<https://devfeed.tech/tags/compute.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [data-center-cloud](<https://devfeed.tech/tags/data-center-cloud.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [dsx](<https://devfeed.tech/tags/dsx.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [featured](<https://devfeed.tech/tags/featured.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [inference](<https://devfeed.tech/tags/inference.md>), [inference-performance](<https://devfeed.tech/tags/inference-performance.md>), [latency](<https://devfeed.tech/tags/latency.md>), [long-context](<https://devfeed.tech/tags/long-context.md>), [memory](<https://devfeed.tech/tags/memory.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [nvfp4](<https://devfeed.tech/tags/nvfp4.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [rubin-gpu](<https://devfeed.tech/tags/rubin-gpu.md>), [scale](<https://devfeed.tech/tags/scale.md>), [tensor-cores](<https://devfeed.tech/tags/tensor-cores.md>), [top-stories](<https://devfeed.tech/tags/top-stories.md>), [training](<https://devfeed.tech/tags/training.md>), [vera-rubin](<https://devfeed.tech/tags/vera-rubin.md>)

### 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....

## NVIDIA NVLink: The Scale-Up Network for AI Factories

DevFeed: [NVIDIA NVLink: The Scale-Up Network for AI Factories](<https://devfeed.tech/articles/nvidia-nvlink-the-scale-up-network-for-ai-factories-6905.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/nvidia-nvlink-the-scale-up-network-for-ai-factories/>)

Author: Elizabeth Goodman

Published: 2026-07-20T15:46:28Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [NVLink](<https://devfeed.tech/topics/nvlink.md>), [AI Factory](<https://devfeed.tech/topics/ai-factory.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [networking](<https://devfeed.tech/topics/networking.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [datacenter](<https://devfeed.tech/topics/datacenter.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [Inference Performance](<https://devfeed.tech/topics/inference-performance.md>), [Low Latency](<https://devfeed.tech/topics/low-latency.md>)

Tags: [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-factory](<https://devfeed.tech/tags/ai-factory.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [collective](<https://devfeed.tech/tags/collective.md>), [communication](<https://devfeed.tech/tags/communication.md>), [compute](<https://devfeed.tech/tags/compute.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [featured](<https://devfeed.tech/tags/featured.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [inference](<https://devfeed.tech/tags/inference.md>), [infiniband](<https://devfeed.tech/tags/infiniband.md>), [latency](<https://devfeed.tech/tags/latency.md>), [low-latency](<https://devfeed.tech/tags/low-latency.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [networking](<https://devfeed.tech/tags/networking.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [nvlink](<https://devfeed.tech/tags/nvlink.md>), [production](<https://devfeed.tech/tags/production.md>), [scale](<https://devfeed.tech/tags/scale.md>), [spectrum-ethernet](<https://devfeed.tech/tags/spectrum-ethernet.md>), [spectrum-x](<https://devfeed.tech/tags/spectrum-x.md>), [speed](<https://devfeed.tech/tags/speed.md>), [systems](<https://devfeed.tech/tags/systems.md>), [vera-rubin](<https://devfeed.tech/tags/vera-rubin.md>)

### AI overview

NVIDIA NVLink is presented as a scale-up networking fabric for AI factories. It provides high-bandwidth, low-latency GPU-to-GPU communication for large AI inference, training, and parallel-computing workloads, with collective-operation acceleration and rack-level resiliency.

### Source excerpt

The demand for AI continues to accelerate. Workloads are getting larger, models are becoming more complex, and there is mounting pressure to deploy AI compute...

## Welcome Inkling by Thinking Machines

DevFeed: [Welcome Inkling by Thinking Machines](<https://devfeed.tech/articles/welcome-inkling-by-thinking-machines-7502.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/thinkingmachines-inkling>)

Author: ben burtenshaw; merve; Pedro Cuenca; Aritra Roy Gosthipaty; Andres Marafioti

Published: 2026-07-15T00:00:00Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>), [hugging face](<https://devfeed.tech/topics/hugging-face.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [Deployment](<https://devfeed.tech/topics/deployment.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [sglang](<https://devfeed.tech/topics/sglang.md>)

Tags: [announcement](<https://devfeed.tech/tags/announcement.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [audio](<https://devfeed.tech/tags/audio.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [generation](<https://devfeed.tech/tags/generation.md>), [inference](<https://devfeed.tech/tags/inference.md>), [inference-endpoints](<https://devfeed.tech/tags/inference-endpoints.md>), [llama-cpp](<https://devfeed.tech/tags/llama-cpp.md>), [llms](<https://devfeed.tech/tags/llms.md>), [mixture-of-experts](<https://devfeed.tech/tags/mixture-of-experts.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [moe](<https://devfeed.tech/tags/moe.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [sglang](<https://devfeed.tech/tags/sglang.md>), [transformers](<https://devfeed.tech/tags/transformers.md>), [vllm](<https://devfeed.tech/tags/vllm.md>)

### AI overview

Thinking Machines Lab's Inkling is presented as a large open multimodal language model that accepts image, text, and audio inputs. The article covers its mixture-of-experts architecture, million-token context window, reasoning across modalities, fine-tuning use cases, model variants, and deployment through Hugging Face Inference Endpoints and inference frameworks.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.

## 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](<https://devfeed.tech/articles/reducing-high-bandwidth-memory-bottlenecks-in-jax-based-llm-training-with-host-offloading-6925.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/reducing-high-bandwidth-memory-bottlenecks-in-jax-based-llm-training-with-host-offloading/>)

Author: Tanya Lenz

Published: 2026-07-10T18:17:40Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [LLM Techniques](<https://devfeed.tech/topics/llm-techniques.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [NVLink](<https://devfeed.tech/topics/nvlink.md>), [systems](<https://devfeed.tech/topics/systems.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>)

Tags: [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [blackwell](<https://devfeed.tech/tags/blackwell.md>), [compute](<https://devfeed.tech/tags/compute.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [featured](<https://devfeed.tech/tags/featured.md>), [gb200](<https://devfeed.tech/tags/gb200.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [grace-cpu](<https://devfeed.tech/tags/grace-cpu.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-techniques](<https://devfeed.tech/tags/llm-techniques.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [nvl72](<https://devfeed.tech/tags/nvl72.md>), [nvlink](<https://devfeed.tech/tags/nvlink.md>), [simulation-modeling-design](<https://devfeed.tech/tags/simulation-modeling-design.md>), [training-ai-models](<https://devfeed.tech/tags/training-ai-models.md>), [vera-rubin](<https://devfeed.tech/tags/vera-rubin.md>), [work](<https://devfeed.tech/tags/work.md>)

### 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,...

## A Jargon-Free Learning Hub for AI Foundations

DevFeed: [A Jargon-Free Learning Hub for AI Foundations](<https://devfeed.tech/articles/i-m-building-the-best-spot-for-learning-ai-foundations-on-the-internet-18350.md>)

Original publisher: [Read original article](<https://bamania-ashish.medium.com/im-building-the-best-spot-for-learning-ai-foundations-on-the-internet-0cca03daf582?source=rss-f10e9a50984a------2>)

Author: Dr. Ashish Bamania

Published: 2026-07-04T11:28:14Z

Content type: opinion

Language: en

Sources: [Dr. Ashish Bamania](<https://devfeed.tech/sources/dr-ashish-bamania.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [llm](<https://devfeed.tech/tags/llm.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [programming](<https://devfeed.tech/tags/programming.md>), [publications](<https://devfeed.tech/tags/publications.md>), [technology](<https://devfeed.tech/tags/technology.md>)

### AI overview

The author announces a learning resource focused on high-quality, jargon-free information about Artificial Intelligence. Its planned lessons cover how LLMs generate text, building and training an LLM from scratch, NVIDIA GPUs for AI engineers, and building and training a Mixture-of-Experts LLM from scratch.

### Source excerpt

Photo by Google DeepMind on Unsplash 👋🏻 Hey everyone! The internet is full of publications that buzz about every new model release, churn out hot takes on who's winning in AI, and spew doom-and-gloom hype (plus a hundred "10 prompts that will change your life" posts). None of them have made a meaningful difference in my life. Rather, this content is written to provoke emotions and go viral. I have a deep dislike for this type of writing. So, I am fixing this by going the other way and creating a spot where you can find very high-quality, jargon-free information about Artificial Intelligence. Here are four lessons that describe what I'm talking about. A hardware-level tour of how LLMs generate text Build and train an LLM from scratch What every AI engineer must know about NVIDIA GPUs Build and Train a Mixture-of-Experts (MoE) LLM from Scratch If you're interested in really leveling up as an AI engineer, here's your link to join me alongside 10,000+ other smart engineers 👉🏻 Into AI Cheers!

## DiffusionGemma: 4x faster text generation

DevFeed: [DiffusionGemma: 4x faster text generation](<https://devfeed.tech/articles/diffusiongemma-4x-faster-text-generation-6147.md>)

Original publisher: [Read original article](<https://deepmind.google/blog/diffusiongemma-4x-faster-text-generation/>)

Author: Brendan O'Donoghue

Published: 2026-06-10T16:24:11Z

Content type: release

Language: en

Sources: [Google DeepMind News](<https://devfeed.tech/sources/google-deepmind-news.md>)

Topics: [Language models](<https://devfeed.tech/topics/language-models.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>)

Tags: [diffusion](<https://devfeed.tech/tags/diffusion.md>), [gemma](<https://devfeed.tech/tags/gemma.md>), [inference](<https://devfeed.tech/tags/inference.md>), [latency](<https://devfeed.tech/tags/latency.md>), [local](<https://devfeed.tech/tags/local.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [none](<https://devfeed.tech/tags/none.md>), [text-generation](<https://devfeed.tech/tags/text-generation.md>)

### AI overview

DiffusionGemma is an experimental Apache 2.0-licensed 26B MoE text-diffusion model that generates text blocks in parallel for up to 4x faster GPU generation. It targets speed-critical local interactive workflows, while standard Gemma 4 remains recommended for maximum output quality.

### Source excerpt

An overview of DiffusionGemma, an exceptionally fast text generation model with up to 4x faster speeds.

## Introducing Gemma 4 12B: a unified, encoder-free multimodal model

DevFeed: [Introducing Gemma 4 12B: a unified, encoder-free multimodal model](<https://devfeed.tech/articles/introducing-gemma-4-12b-a-unified-encoder-free-multimodal-model-6204.md>)

Original publisher: [Read original article](<https://deepmind.google/blog/introducing-gemma-4-12b-a-unified-encoder-free-multimodal-model/>)

Author: Olivier Lacombe

Published: 2026-06-09T14:10:19Z

Content type: article

Language: en

Sources: [Google DeepMind News](<https://devfeed.tech/sources/google-deepmind-news.md>)

Topics: [gemma4](<https://devfeed.tech/topics/gemma4.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>), [Language models](<https://devfeed.tech/topics/language-models.md>), [moe](<https://devfeed.tech/topics/moe.md>), [Hardware](<https://devfeed.tech/topics/hardware.md>), [Latency](<https://devfeed.tech/topics/latency.md>)

Tags: [apache](<https://devfeed.tech/tags/apache.md>), [community](<https://devfeed.tech/tags/community.md>), [gemma](<https://devfeed.tech/tags/gemma.md>), [laptop](<https://devfeed.tech/tags/laptop.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm](<https://devfeed.tech/tags/llm.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [none](<https://devfeed.tech/tags/none.md>)

### AI overview

Gemma 4 12B is an encoder-free multimodal model designed to deliver agentic intelligence locally on laptops. It combines native vision and audio processing, near-26B benchmark performance, a reduced memory footprint, and Apache 2.0 licensing.

### Source excerpt

An overview of Gemma 4 12B, a model designed to bring high-performance multimodal intelligence directly to your laptop.

## Gemma 4: Byte for byte, the most capable open models

DevFeed: [Gemma 4: Byte for byte, the most capable open models](<https://devfeed.tech/articles/gemma-4-byte-for-byte-the-most-capable-open-models-6176.md>)

Original publisher: [Read original article](<https://deepmind.google/blog/gemma-4-byte-for-byte-the-most-capable-open-models/>)

Author: Clement Farabet

Published: 2026-04-02T16:00:49Z

Content type: release

Language: en

Sources: [Google DeepMind News](<https://devfeed.tech/sources/google-deepmind-news.md>)

Topics: [gemma4](<https://devfeed.tech/topics/gemma4.md>), [gemma](<https://devfeed.tech/topics/gemma.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>), [Low Latency](<https://devfeed.tech/topics/low-latency.md>), [Android](<https://devfeed.tech/topics/android.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [android](<https://devfeed.tech/tags/android.md>), [apache](<https://devfeed.tech/tags/apache.md>), [gemma](<https://devfeed.tech/tags/gemma.md>), [latency](<https://devfeed.tech/tags/latency.md>), [low-latency](<https://devfeed.tech/tags/low-latency.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [models](<https://devfeed.tech/tags/models.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [none](<https://devfeed.tech/tags/none.md>), [on-device](<https://devfeed.tech/tags/on-device.md>), [open](<https://devfeed.tech/tags/open.md>), [performance](<https://devfeed.tech/tags/performance.md>), [products](<https://devfeed.tech/tags/products.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [research](<https://devfeed.tech/tags/research.md>), [tools](<https://devfeed.tech/tags/tools.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

Gemma 4 is a family of open models designed for advanced reasoning and agentic workflows. It includes E2B, E4B, 26B Mixture of Experts, and 31B Dense variants, with an Apache 2.0 license and designs optimized for hardware ranging from Android devices and laptop GPUs to developer workstations and accelerators.

### Source excerpt

Gemma 4: Our most intelligent open models to date, purpose-built for advanced reasoning and agentic workflows.

## Introducing Mistral Small 4

DevFeed: [Introducing Mistral Small 4](<https://devfeed.tech/articles/introducing-mistral-small-4-7082.md>)

Original publisher: [Read original article](<https://mistral.ai/news/mistral-small-4/>)

Published: 2026-03-16T21:00:00Z

Content type: release

Language: en

Sources: [Mistral AI Blog](<https://devfeed.tech/sources/mistral-ai-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Nemotron](<https://devfeed.tech/topics/nemotron.md>), [long-context](<https://devfeed.tech/topics/long-context.md>), [Low Latency](<https://devfeed.tech/topics/low-latency.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>)

Tags: [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [ai](<https://devfeed.tech/tags/ai.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [latency](<https://devfeed.tech/tags/latency.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [models](<https://devfeed.tech/tags/models.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [nemotron](<https://devfeed.tech/tags/nemotron.md>), [net](<https://devfeed.tech/tags/net.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [open](<https://devfeed.tech/tags/open.md>), [open-source](<https://devfeed.tech/tags/open-source.md>)

### AI overview

Mistral announces Mistral Small 4, a hybrid open model that combines instruction following, reasoning, multimodal understanding, and agentic coding in one system. It accepts text and image inputs, uses a Mixture-of-Experts architecture with a 256k context window, offers configurable reasoning effort, and reports lower latency and higher throughput than Mistral Small 3.

### Source excerpt

The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.

## Architectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeek

DevFeed: [Architectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeek](<https://devfeed.tech/articles/architectural-choices-in-china-s-open-source-ai-ecosystem-building-beyond-deepseek-7251.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/huggingface/one-year-since-the-deepseek-moment-blog-2>)

Author: Adina Yakefu; Irene Solaiman

Published: 2026-01-27T15:01:45Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [Open Source](<https://devfeed.tech/topics/open-source.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [Hardware](<https://devfeed.tech/topics/hardware.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [model-deployment](<https://devfeed.tech/topics/model-deployment.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [toolchains](<https://devfeed.tech/topics/toolchains.md>), [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [china](<https://devfeed.tech/tags/china.md>), [compute](<https://devfeed.tech/tags/compute.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [performance](<https://devfeed.tech/tags/performance.md>), [text-to-image](<https://devfeed.tech/tags/text-to-image.md>), [toolchains](<https://devfeed.tech/tags/toolchains.md>)

### AI overview

This second article in a three-part series examines architectural and hardware choices in China's open-source AI ecosystem after the DeepSeek Moment. It explains why Mixture-of-Experts architectures became widespread, emphasizing flexible compute allocation, sustainable cost-performance balance, deployment across varied hardware, and expansion into multimodal models, agents, datasets, evaluation, and toolchains.

### Source excerpt

This is the second blog in a three-part series on China's open source community's historical advancements since January 2025's "DeepSeek Moment." The first blog is available here, and the third blog is available here. In this second piece we turn our focus from models to the architectural and hardware choices Chinese companies have made as openness becomes the norm.

## 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](<https://devfeed.tech/articles/google-cloud-c4-brings-a-70-tco-improvement-on-gpt-oss-with-intel-and-hugging-face-7220.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/gpt-oss-on-intel-xeon>)

Author: Jiqing.Feng; Matrix Yao; Ke Ding; Ilyas Moutawwakil

Published: 2025-10-16T00:00:00Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [moe](<https://devfeed.tech/topics/moe.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [AI, ML & Data Engineering](<https://devfeed.tech/topics/ai-ml-data-engineering.md>)

Tags: [cpu](<https://devfeed.tech/tags/cpu.md>), [google-cloud](<https://devfeed.tech/tags/google-cloud.md>), [gpt-oss](<https://devfeed.tech/tags/gpt-oss.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [inference](<https://devfeed.tech/tags/inference.md>), [intel](<https://devfeed.tech/tags/intel.md>), [llm](<https://devfeed.tech/tags/llm.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [performance](<https://devfeed.tech/tags/performance.md>)

### 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.

[Next page](<https://devfeed.tech/tags/mixture-of-experts-moe.md?cursor=WyIyMDI1LTEwLTE2VDAwOjAwOjAwKzAwOjAwIiwgImFlOGZmYmI1LTI5NmUtNGIxYS1iYWU1LTRiZjgwOGNkOGMzMiJd>)