# Thor

Published articles for Thor.

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

## TensorRT Edge-LLM Completes the MLPerf Edge Agentic Benchmark 6.4x Faster on Jetson AGX Thor

DevFeed: [TensorRT Edge-LLM Completes the MLPerf Edge Agentic Benchmark 6.4x Faster on Jetson AGX Thor](<https://devfeed.tech/articles/tensorrt-edge-llm-completes-the-mlperf-edge-agentic-benchmark-6-4x-faster-on-jetson-agx-thor-31485.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/tensorrt-edge-llm-completes-the-mlperf-edge-agentic-benchmark-6-4x-faster-on-jetson-agx-thor/>)

Author: Elizabeth Goodman

Published: 2026-09-16T20:37:07Z

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: [Jetson AGX Thor Developer Kit](<https://devfeed.tech/topics/jetson-agx-thor-developer-kit.md>), [Inference Performance](<https://devfeed.tech/topics/inference-performance.md>), [benchmarking](<https://devfeed.tech/topics/benchmarking.md>), [TensorRT](<https://devfeed.tech/topics/tensorrt.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [quantization](<https://devfeed.tech/topics/quantization.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>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [jetson](<https://devfeed.tech/tags/jetson.md>), [jetson-agx-thor-developer-kit](<https://devfeed.tech/tags/jetson-agx-thor-developer-kit.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-benchmarking](<https://devfeed.tech/tags/llm-benchmarking.md>), [mlperf](<https://devfeed.tech/tags/mlperf.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [performance](<https://devfeed.tech/tags/performance.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [tensorrt](<https://devfeed.tech/tags/tensorrt.md>), [tensorrt-llm](<https://devfeed.tech/tags/tensorrt-llm.md>), [thor](<https://devfeed.tech/tags/thor.md>)

### AI overview

This article reports that NVIDIA TensorRT Edge-LLM ran Qwen3.6-27B on a single NVIDIA Jetson AGX Thor Developer Kit for the MLPerf Inference v6.1 Edge Agentic benchmark. Using NVFP4 quantization, tree-based multi-token prediction, and KV cache reuse, it achieved 52.33 tokens per second and completed 1,007 turns in 24 minutes and 36 seconds, 6.4 times faster than the llama.cpp reference submission.

### Source excerpt

AI agents are moving from cloud data centers to vehicles, robots, and other edge devices. Unlike a chatbot that answers a single prompt, an agent works through...

## 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...

## Security Week 2636: атака GPUThor обходит защиту ECC

DevFeed: [Security Week 2636: атака GPUThor обходит защиту ECC](<https://devfeed.tech/articles/security-week-2636-gputhor-ecc-23093.md>)

Original publisher: [Read original article](<https://habr.com/ru/companies/kaspersky/articles/1076720/>)

Author: Kaspersky\_Lab ("Лаборатория Касперского")

Published: 2026-08-31T14:24:08Z

Content type: news

Language: ru

Sources: ["Лаборатория Касперского" RU](<https://devfeed.tech/sources/ru-2.md>)

Topics: [rowhammer](<https://devfeed.tech/topics/rowhammer.md>), [Security](<https://devfeed.tech/topics/security.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [ampere](<https://devfeed.tech/tags/ampere.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [rowhammer](<https://devfeed.tech/tags/rowhammer.md>), [security](<https://devfeed.tech/tags/security.md>), [tag-9fe8963de219](<https://devfeed.tech/tags/tag-9fe8963de219.md>), [tag-cc2a6346d835](<https://devfeed.tech/tags/tag-cc2a6346d835.md>), [thor](<https://devfeed.tech/tags/thor.md>)

### AI overview

Researchers from the University of Toronto demonstrated GPUThor, a Rowhammer attack targeting NVIDIA Ampere A4000, A4500, A5000, and A6000 professional GPUs. The attack can produce double and triple bit flips that ECC does not correct, enabling denial-of-service and theoretically creating conditions for privilege escalation.

### Source excerpt

Исследователи из канадского Университета Торонто на прошлой неделе опубликовали научную работу, в которой продемонстрировали новую атаку на видеоускорители NVIDIA. Атака, получившая название GPUThor, относится к классу Rowhammer, то есть использует многократные обращения к ячейкам оперативной памяти с целью повлиять на соседние ячейки. Таким образом можно изменить данные в областях памяти, изначально недоступных потенциальному злоумышленнику. Наиболее актуален такой сценарий атаки в случае совместного доступа к профессиональному видеоускорителю. Именно поэтому в подобных работах традиционно исследуются устройства NVIDIA, в данном случае модели поколения Ampere A4000, A4500, A5000 и A6000. По сравнению с предыдущими атаками на подобные устройства, продемонстрированными в начале 2026 года, GPUThor обеспечивает изменение данных в целевых ячейках в сотни и даже тысячи раз чаще. Но самое главное -- новая атака в некоторых случаях приводит к двойным и тройным бит-флипам, которые не корректируются системой ECC. Это точно позволяет провести атаку типа "отказ в обслуживании" и теоретически создает условия для атаки с повышением привилегий, даже если коррекция ошибок включена. Читать далее

## Post-Train NVIDIA Cosmos 3 Edge for On-Device Robot Control

DevFeed: [Post-Train NVIDIA Cosmos 3 Edge for On-Device Robot Control](<https://devfeed.tech/articles/post-train-nvidia-cosmos-3-edge-for-on-device-robot-control-6920.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/post-train-nvidia-cosmos-3-edge-for-on-device-robot-control/>)

Author: Michelle Horton

Published: 2026-08-19T16:00:00Z

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

Tags: [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [cosmos](<https://devfeed.tech/tags/cosmos.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [edge](<https://devfeed.tech/tags/edge.md>), [edge-computing](<https://devfeed.tech/tags/edge-computing.md>), [featured](<https://devfeed.tech/tags/featured.md>), [foundation-models](<https://devfeed.tech/tags/foundation-models.md>), [inference](<https://devfeed.tech/tags/inference.md>), [jetson](<https://devfeed.tech/tags/jetson.md>), [latency](<https://devfeed.tech/tags/latency.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [on-device](<https://devfeed.tech/tags/on-device.md>), [physical-ai](<https://devfeed.tech/tags/physical-ai.md>), [post-training](<https://devfeed.tech/tags/post-training.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [robotics-simulation](<https://devfeed.tech/tags/robotics-simulation.md>), [robots](<https://devfeed.tech/tags/robots.md>), [simulation-modeling-design](<https://devfeed.tech/tags/simulation-modeling-design.md>), [thor](<https://devfeed.tech/tags/thor.md>), [tutorial](<https://devfeed.tech/tags/tutorial.md>)

### AI overview

A tutorial on post-training NVIDIA Cosmos 3 Edge as an on-device robot manipulation policy, serving it on Jetson Thor, running receding-horizon inference, and evaluating it in closed-loop simulation.

### Source excerpt

Robots need policies that can adapt to their sensors, environments, and tasks while running on onboard computing hardware. World models offer a foundation for...

## Beyond VLAs: How World Action Models Reshape Robot Manipulation

DevFeed: [Beyond VLAs: How World Action Models Reshape Robot Manipulation](<https://devfeed.tech/articles/beyond-vlas-how-world-action-models-reshape-robot-manipulation-6764.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/beyond-vlas-how-world-action-models-reshape-robot-manipulation/>)

Author: Michelle Horton

Published: 2026-08-04T16:00:00Z

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: [Robotics](<https://devfeed.tech/topics/robotics.md>), [World models](<https://devfeed.tech/topics/world-models.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [post-training](<https://devfeed.tech/topics/post-training.md>), [Cosmos](<https://devfeed.tech/topics/cosmos.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [NVIDIA Research](<https://devfeed.tech/topics/nvidia-research.md>)

Tags: [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [cosmos](<https://devfeed.tech/tags/cosmos.md>), [featured](<https://devfeed.tech/tags/featured.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [nvidia-research](<https://devfeed.tech/tags/nvidia-research.md>), [physical-ai](<https://devfeed.tech/tags/physical-ai.md>), [post-training](<https://devfeed.tech/tags/post-training.md>), [robot-manipulation](<https://devfeed.tech/tags/robot-manipulation.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [simulation-modeling-design](<https://devfeed.tech/tags/simulation-modeling-design.md>), [thor](<https://devfeed.tech/tags/thor.md>), [vlm](<https://devfeed.tech/tags/vlm.md>), [world-model](<https://devfeed.tech/tags/world-model.md>), [zero-shot](<https://devfeed.tech/tags/zero-shot.md>)

### AI overview

The article explains how World Action Models (WAMs) use video world models as backbones for robot policies, addressing the physical-generalization limitations of vision-language-action models. It discusses post-training WAMs into specialized policies and presents NVIDIA Cosmos 3 as a foundation for building them.

### Source excerpt

A central challenge in robotics is building policies that generalize beyond the demonstrations they're trained on. A policy that succeeds in a training scene...

## Exploring CLI Best Practices

DevFeed: [Exploring CLI Best Practices](<https://devfeed.tech/articles/exploring-cli-best-practices-28625.md>)

Original publisher: [Read original article](<https://eng.localytics.com/exploring-cli-best-practices/>)

Author: Kevin Deisz

Published: 2016-10-11T19:25:23Z

Content type: tutorial

Language: en

Sources: [Localytics](<https://devfeed.tech/sources/localytics.md>)

Topics: [Command-line interface](<https://devfeed.tech/topics/cli.md>), [Ruby](<https://devfeed.tech/topics/ruby.md>), [Thor](<https://devfeed.tech/topics/thor.md>), [Tooling](<https://devfeed.tech/topics/tooling.md>), [User Experience](<https://devfeed.tech/topics/user-experience.md>)

Tags: [bash](<https://devfeed.tech/tags/bash.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [cli](<https://devfeed.tech/tags/cli.md>), [command-line](<https://devfeed.tech/tags/command-line.md>), [ruby](<https://devfeed.tech/tags/ruby.md>), [thor](<https://devfeed.tech/tags/thor.md>), [tooling](<https://devfeed.tech/tags/tooling.md>), [user-experience](<https://devfeed.tech/tags/user-experience.md>)

### AI overview

Localytics describes best practices for designing intuitive command-line interfaces, based on its experience refining internal Ruby CLIs built with Thor. The recommendations include providing sensible defaults, offering readable options with short aliases, following common command-line conventions, and allowing users to identify files explicitly.

### Source excerpt

At Localytics we build command line interfaces that manage our infrastructure and processes. This is our list of best practices that we've learned.