#edgeai — Public Fediverse posts

Встреча FPGA-сообщества: онлайн, вечер, пять докладов

Регулярный слет сообщества FPGA-инженеров и им причастных пройдет 26 мая в 19 часов в формате онлайн-трансляции. В программе вечера пять докладов: о Yosys, SystemRDL, Edge AI и анализе вейвформ с LLM. Подробности о темах и спикерах — под катом. А регистрация —

https://habr.com/ru/companies/yadro/articles/1034776/

#fpga #митап #yosys #systemrdl #edgeai

Встреча FPGA-сообщества: онлайн, вечер, пять докладов

Регулярный слет сообщества FPGA-инженеров и им причастных пройдет 26 мая в 19 часов в формате онлайн-трансляции. В программе вечера пять докладов: о Yosys, SystemRDL, Edge AI и анализе вейвформ с LLM. Подробности о темах и спикерах — под катом. А регистрация —

https://habr.com/ru/companies/yadro/articles/1034776/

#fpga #митап #yosys #systemrdl #edgeai

Встреча FPGA-сообщества: онлайн, вечер, пять докладов

Регулярный слет сообщества FPGA-инженеров и им причастных пройдет 26 мая в 19 часов в формате онлайн-трансляции. В программе вечера пять докладов: о Yosys, SystemRDL, Edge AI и анализе вейвформ с LLM. Подробности о темах и спикерах — под катом. А регистрация —

https://habr.com/ru/companies/yadro/articles/1034776/

#fpga #митап #yosys #systemrdl #edgeai

Встреча FPGA-сообщества: онлайн, вечер, пять докладов

Регулярный слет сообщества FPGA-инженеров и им причастных пройдет 26 мая в 19 часов в формате онлайн-трансляции. В программе вечера пять докладов: о Yosys, SystemRDL, Edge AI и анализе вейвформ с LLM. Подробности о темах и спикерах — под катом. А регистрация —

https://habr.com/ru/companies/yadro/articles/1034776/

#fpga #митап #yosys #systemrdl #edgeai

ICYMI 👉 Faster pipelines, smarter inference, and sharper playback.

How our multimedia engineering team helped shape GStreamer 1.28 with hardware acceleration, zero-copy improvements, HDR and color support, AI integration, and key codec, RTP, and WebRTC fixes: http://www.collabora.com/news-and-blog/news-and-events/16-contributors-cross-stack-improvements-collabora-work-gstreamer-128.html

#GStreamer #AIInference #ComputerVision #EdgeAI

ICYMI 👉 Faster pipelines, smarter inference, and sharper playback.

How our multimedia engineering team helped shape GStreamer 1.28 with hardware acceleration, zero-copy improvements, HDR and color support, AI integration, and key codec, RTP, and WebRTC fixes: http://www.collabora.com/news-and-blog/news-and-events/16-contributors-cross-stack-improvements-collabora-work-gstreamer-128.html

#GStreamer #AIInference #ComputerVision #EdgeAI

ICYMI 👉 Faster pipelines, smarter inference, and sharper playback.

How our multimedia engineering team helped shape GStreamer 1.28 with hardware acceleration, zero-copy improvements, HDR and color support, AI integration, and key codec, RTP, and WebRTC fixes: http://www.collabora.com/news-and-blog/news-and-events/16-contributors-cross-stack-improvements-collabora-work-gstreamer-128.html

#GStreamer #AIInference #ComputerVision #EdgeAI

ICYMI 👉 Faster pipelines, smarter inference, and sharper playback.

How our multimedia engineering team helped shape GStreamer 1.28 with hardware acceleration, zero-copy improvements, HDR and color support, AI integration, and key codec, RTP, and WebRTC fixes: http://www.collabora.com/news-and-blog/news-and-events/16-contributors-cross-stack-improvements-collabora-work-gstreamer-128.html

#GStreamer #AIInference #ComputerVision #EdgeAI

ICYMI 👉 Faster pipelines, smarter inference, and sharper playback.

How our multimedia engineering team helped shape GStreamer 1.28 with hardware acceleration, zero-copy improvements, HDR and color support, AI integration, and key codec, RTP, and WebRTC fixes: http://www.collabora.com/news-and-blog/news-and-events/16-contributors-cross-stack-improvements-collabora-work-gstreamer-128.html

#GStreamer #AIInference #ComputerVision #EdgeAI

A $1,999 Mac mini runs a 70B parameter model that a $4,000 Windows workstation physically cannot.
The reason: Apple Silicon's unified memory. No separate VRAM pool. No PCIe bottleneck. Just one shared memory for CPU, GPU, and Neural Engine.
Full breakdown： https://www.buysellram.com/blog/why-mac-mini-is-the-surprising-frontrunner-for-local-ai-agents/

#ArtificialIntelligence #AI #LocalAI #MacMini #AppleSilicon #LLM #AIAgents #MachineLearning #EdgeAI #TechInfrastructure #DataPrivacy #Automation #AIHardware

A $1,999 Mac mini runs a 70B parameter model that a $4,000 Windows workstation physically cannot.
The reason: Apple Silicon's unified memory. No separate VRAM pool. No PCIe bottleneck. Just one shared memory for CPU, GPU, and Neural Engine.
Full breakdown： https://www.buysellram.com/blog/why-mac-mini-is-the-surprising-frontrunner-for-local-ai-agents/

#ArtificialIntelligence #AI #LocalAI #MacMini #AppleSilicon #LLM #AIAgents #MachineLearning #EdgeAI #TechInfrastructure #DataPrivacy #Automation #AIHardware

A $1,999 Mac mini runs a 70B parameter model that a $4,000 Windows workstation physically cannot.
The reason: Apple Silicon's unified memory. No separate VRAM pool. No PCIe bottleneck. Just one shared memory for CPU, GPU, and Neural Engine.
Full breakdown： https://www.buysellram.com/blog/why-mac-mini-is-the-surprising-frontrunner-for-local-ai-agents/

#ArtificialIntelligence #AI #LocalAI #MacMini #AppleSilicon #LLM #AIAgents #MachineLearning #EdgeAI #TechInfrastructure #DataPrivacy #Automation #AIHardware

The rise of local AI is changing hardware demand in unexpected ways — and the Mac Mini is emerging as one of the biggest winners.

What makes it interesting is not just the compact form factor. Apple Silicon’s unified memory architecture, low power consumption, quiet operation, and ability to run AI workloads locally are making the Mac Mini increasingly attractive for developers, startups, and businesses building AI agents.

Recent reports show that higher-memory Mac Mini configurations are experiencing major shortages as AI adoption accelerates.

This article explores:
• Why local AI agents are growing rapidly
• How the Mac Mini became a practical AI workstation
• The role of unified memory for LLM workloads
• Why developers are moving away from cloud-only AI setups
• What this trend means for future AI infrastructure

https://www.buysellram.com/blog/why-mac-mini-is-the-surprising-frontrunner-for-local-ai-agents/

#ArtificialIntelligence #AI #LocalAI #MacMini #AppleSilicon #LLM #AIAgents #MachineLearning #EdgeAI #DataPrivacy #Automation #AIHardware #technology

A $1,999 Mac mini runs a 70B parameter model that a $4,000 Windows workstation physically cannot.
The reason: Apple Silicon's unified memory. No separate VRAM pool. No PCIe bottleneck. Just one shared memory for CPU, GPU, and Neural Engine.
Full breakdown： https://www.buysellram.com/blog/why-mac-mini-is-the-surprising-frontrunner-for-local-ai-agents/

#ArtificialIntelligence #AI #LocalAI #MacMini #AppleSilicon #LLM #AIAgents #MachineLearning #EdgeAI #TechInfrastructure #DataPrivacy #Automation #AIHardware #tech

We’re headed to the Embedded Vision Summit 2026.
Meet our team at the @cadence booth #402 as we showcase an exciting edge-intelligence demo.
If you’re attending, make sure to stop by and speak to our team.
#EmbeddedAI #EdgeAI #EVS #Embeddedsystems #AI #EmbeddedVisionSummit

MicroVision + Avular : cap sur des drones qui “voient” et décident seuls en temps réel. Lidar + IA embarquée pour l'autonomie. www.webdisclosure.com/article/micr... #Innovation #AI #Aerospace #Drones #Autonomy #Lidar #DefenseTech #EdgeAI

MicroVision, Inc. (NASDAQ:MVIS...

Renesas RZ/V2H Robotics Development Kit handles AI vision, motor control, and power management with a single board

https://fed.brid.gy/r/https://www.cnx-software.com/2026/05/05/renesas-rz-v2h-robotics-development-kit-handles-ai-vision-motor-control-and-power-management-with-a-single-board/

Forlinx UP4 – A 40×40 mm LCC + LGA system-on-module family with Rockchip, NXP, and Allwinner CPU options

Forlinx Embedded UP4 is a new family of pin-to-pin compatible system-on-modules currently offered with Rockchip RK3568J/RK3562J, NXP i.MX…
#Netherlands #Nederland #NL #Europe #Europa #EU #NXP #allwinner #edgeAI #forlinx #hmi #industrial #Linux #networking #qt #rockchip #som
https://www.europesays.com/netherlands/7869/

The preachers of the Silicon Valley Church sell the harvesting of the body as “algorithmic inevitability,” promising immortality. A neat fable. Maybe they’ll keep the data lords alive for 150 years—but half of it will be Alzheimer’s. In the end, the thermodynamic hammer still falls.
#Transhumanizm #DataEngineering #CRISPR #EdgeAI #GenerativeAI #FederatedLearning #MachineLearning #DataScience #AITools #AIAutomation #CloudComputing #SyntheticData #SyntheticData #AntiHarari #MLOps #Longevity

$4,290+ Unitree R1-A5 and R2-A7 humanoid robots features grippers or dexterous hands, fixed or wheeled base

https://fed.brid.gy/r/https://www.cnx-software.com/2026/05/01/4290-unitree-r1-a5-and-r2-a7-humanoid-robots-features-gripper-or-dexterous-hands-fixed-or-wheeled-base/

$4,290+ Unitree R1-A5 and R2-A7 humanoid robots features grippers or dexterous hands, fixed or wheeled base

https://web.brid.gy/r/https://www.cnx-software.com/2026/05/01/4290-unitree-r1-a5-and-r2-a7-humanoid-robots-features-gripper-or-dexterous-hands-fixed-or-wheeled-base/

$4,290+ Unitree R1-A5 and R2-A7 humanoid robots features grippers or dexterous hands, fixed or wheeled base

https://web.brid.gy/r/https://www.cnx-software.com/2026/05/01/4290-unitree-r1-a5-and-r2-a7-humanoid-robots-features-gripper-or-dexterous-hands-fixed-or-wheeled-base/

$4,290+ Unitree R1-A5 and R2-A7 humanoid robots features grippers or dexterous hands, fixed or wheeled base

https://web.brid.gy/r/https://www.cnx-software.com/2026/05/01/4290-unitree-r1-a5-and-r2-a7-humanoid-robots-features-gripper-or-dexterous-hands-fixed-or-wheeled-base/

$4,290+ Unitree R1-A5 and R2-A7 humanoid robots features grippers or dexterous hands, fixed or wheeled base

https://web.brid.gy/r/https://www.cnx-software.com/2026/05/01/4290-unitree-r1-a5-and-r2-a7-humanoid-robots-features-gripper-or-dexterous-hands-fixed-or-wheeled-base/

Forlinx UP4 – A 40×40 mm LCC + LGA system-on-module family with Rockchip, NXP, and Allwinner CPU options

https://fed.brid.gy/r/https://www.cnx-software.com/2026/04/30/forlinx-up4-a-40x40-mm-lcc-lga-system-on-module-family-with-rockchip-nxp-and-allwinner-cpu-options/

Edge AI: Архитектура, технологии и стратегические перспективы распределённого искусственного интеллекта

Периферийный искусственный интеллект (Edge AI) сегодня является одним из наиболее динамично развивающихся направлений в области машинного обучения и распределённых вычислений...

#DST #DSTGlobal #ДСТ #ДСТГлобал #искусственныйинтеллект #EdgeAI #технологии #Компьютерноезрение #биометрическаяаутентификация #AppleNeuralEngine #Генеративныемодели #LLM

Источник: https://dstglobal.ru/club/1177-edge-ai-arhitektura-tehnologii-i-strategicheskie-perspektivy-raspredelyonnogo-iskusstvennogo-in

Edge AI: Архитектура, технологии и стратегические перспективы распределённого искусственного интеллекта

Периферийный искусственный интеллект (Edge AI) сегодня является одним из наиболее динамично развивающихся направлений в области машинного обучения и распределённых вычислений...

#DST #DSTGlobal #ДСТ #ДСТГлобал #искусственныйинтеллект #EdgeAI #технологии #Компьютерноезрение #биометрическаяаутентификация #AppleNeuralEngine #Генеративныемодели #LLM

Источник: https://dstglobal.ru/club/1177-edge-ai-arhitektura-tehnologii-i-strategicheskie-perspektivy-raspredelyonnogo-iskusstvennogo-in

Edge AI: Архитектура, технологии и стратегические перспективы распределённого искусственного интеллекта

Периферийный искусственный интеллект (Edge AI) сегодня является одним из наиболее динамично развивающихся направлений в области машинного обучения и распределённых вычислений...

#DST #DSTGlobal #ДСТ #ДСТГлобал #искусственныйинтеллект #EdgeAI #технологии #Компьютерноезрение #биометрическаяаутентификация #AppleNeuralEngine #Генеративныемодели #LLM

Источник: https://dstglobal.ru/club/1177-edge-ai-arhitektura-tehnologii-i-strategicheskie-perspektivy-raspredelyonnogo-iskusstvennogo-in

Edge AI: Архитектура, технологии и стратегические перспективы распределённого искусственного интеллекта

Периферийный искусственный интеллект (Edge AI) сегодня является одним из наиболее динамично развивающихся направлений в области машинного обучения и распределённых вычислений...

#DST #DSTGlobal #ДСТ #ДСТГлобал #искусственныйинтеллект #EdgeAI #технологии #Компьютерноезрение #биометрическаяаутентификация #AppleNeuralEngine #Генеративныемодели #LLM

Источник: https://dstglobal.ru/club/1177-edge-ai-arhitektura-tehnologii-i-strategicheskie-perspektivy-raspredelyonnogo-iskusstvennogo-in

Edge AI: Архитектура, технологии и стратегические перспективы распределённого искусственного интеллекта

Периферийный искусственный интеллект (Edge AI) сегодня является одним из наиболее динамично развивающихся направлений в области машинного обучения и распределённых вычислений...

#DST #DSTGlobal #ДСТ #ДСТГлобал #искусственныйинтеллект #EdgeAI #технологии #Компьютерноезрение #биометрическаяаутентификация #AppleNeuralEngine #Генеративныемодели #LLM

Источник: https://dstglobal.ru/club/1177-edge-ai-arhitektura-tehnologii-i-strategicheskie-perspektivy-raspredelyonnogo-iskusstvennogo-in

UGV Beast – An off-road tracked AI robot built for Raspberry Pi 4/5

https://fed.brid.gy/r/https://www.cnx-software.com/2026/04/21/ugv-beast-an-off-road-tracked-ai-robot-built-for-raspberry-pi-4-5/

UGV Beast – An off-road tracked AI robot built for Raspberry Pi 4/5

https://web.brid.gy/r/https://www.cnx-software.com/2026/04/21/ugv-beast-an-off-road-tracked-ai-robot-built-for-raspberry-pi-4-5/

UGV Beast – An off-road tracked AI robot built for Raspberry Pi 4/5

https://web.brid.gy/r/https://www.cnx-software.com/2026/04/21/ugv-beast-an-off-road-tracked-ai-robot-built-for-raspberry-pi-4-5/

UGV Beast – An off-road tracked AI robot built for Raspberry Pi 4/5

https://web.brid.gy/r/https://www.cnx-software.com/2026/04/21/ugv-beast-an-off-road-tracked-ai-robot-built-for-raspberry-pi-4-5/

UGV Beast – An off-road tracked AI robot built for Raspberry Pi 4/5

https://web.brid.gy/r/https://www.cnx-software.com/2026/04/21/ugv-beast-an-off-road-tracked-ai-robot-built-for-raspberry-pi-4-5/

Pironman 5 Pro Max Review – A Raspberry Pi 5 Tower PC case with integrated video and audio capabilities, optional UPS kit

https://fed.brid.gy/r/https://www.cnx-software.com/2026/04/18/pironman-5-pro-max-review-a-raspberry-pi-5-tower-pc-case-with-integrated-video-and-audio-capabilities-ups-kit/

Small Language Models (SLMs) represent a shift toward ultra-efficient, privacy-preserving AI that can run locally and offline. For businesses, that means lower latency, reduced infrastructure costs, and stronger data protection. Dive into practical implications and where SLMs fit into your AI strategy: https://wix.to/NWrnNyX

#AI
#SLMs
#EdgeAI
#Innovation
#DataPrivacy
#MachineLearning

reBot Arm B601-DM – An open-source 6+1 DoF robotic arm for embodied AI and teleoperation applications

https://fed.brid.gy/r/https://www.cnx-software.com/2026/04/17/rebot-arm-b601-dm-an-open-source-61-dof-robotic-arm-for-embodied-ai-and-teleoperation-applications/

Intel Core Series 3 “Wildcat Lake” processor family launched for entry-level laptops and Edge AI systems

https://fed.brid.gy/r/https://www.cnx-software.com/2026/04/17/intel-core-series-3-wildcat-lake-processor-family-launched-for-entry-level-laptops-and-edge-ai-systems/

IP65-rated TWOWIN T808P-G Edge AI computer features 8x GMSL2 cameras, aviation-grade M12/M16 connectors

https://fed.brid.gy/r/https://www.cnx-software.com/2026/04/16/ip65-rated-twowin-t808p-g-edge-ai-computer-features-8x-gmsl2-cameras-aviation-grade-m12-m16-connectors/

Just as the enterprise is wrapping its mind around #scalingAI in data centers, another seismic shift is emerging on the outskirts of corporate networks.

I'm talking about #edgeAI and #physicalAI. Over the last two months, companies ranging from #NVIDIA to #AT&T, #BoozAllenHamilton, #Cisco, #Comcast, #DellTechnologies, #Dynatrace, #HPE and #PersonalAI have been quietly laying the groundwork for the next generation of the internet and #mobilecomputing infrastructure, and the next generation of enterprise applications that run on them, according to industry watchers.

I spent the last few weeks having heady conversations with industry experts about what the next three to five years will hold for #AI cellular networks, robots, mobile phones, and of course, enterprise businesses.

Kicker quote from Bill Vass of Booz Allen:

"When I was at the Pentagon, we commercialized GPS, and I remember telling people that everyone will have a laptop screen in their car. They thought I was crazy, but I never thought about Lyft and Uber and DoorDash -- it's very hard to know, when you enable a capability, how people will use it."

Read the full story here: https://www.techtarget.com/searchitoperations/news/366641741/Edge-and-physical-AI-poised-to-upend-enterprise-networks

via #AIFoundry : Foundry Local is now Generally Available

https://ift.tt/xUnc9oy
#FoundryLocal #GA #GeneralAvailability #FoundryLocalGA #AI #EdgeAI #OnPremiseAI #LocalAI #AIinApps #NoCloud #OfflineAI #CrossPlatform #Windows #macOS #Linux #OpenAICompatible #ONNXRuntime #WinML …

Our multimedia engineering team delivered major improvements to GStreamer 1.28: hardware acceleration and zero-copy pipelines, HDR and color support for Wayland, AI inference integration, plus critical codec and RTP/WebRTC interoperability fixes.

https://www.collabora.com/news-and-blog/news-and-events/16-contributors-cross-stack-improvements-collabora-work-gstreamer-128.html

@gstreamer #GStreamer #AIInference #ComputerVision #EdgeAI

Microsoft brings sovereign edge AI to Industry 4.0 private networks https://www.telecomstechnews.com/news/microsoft-sovereign-edge-ai-industry-4-0-private-networks/ #microsoft #private5g #edgeai #iiot #telecoms #iot #ai #5g #digitaltransformation #industry40 #technology

Agricultural machinery achieves 81% harvest success via edge IoT https://iottechnews.com/news/agricultural-machinery-achieves-81-harvest-success-edge-iot/ #iiot #edgeai #agriculture #farming #iot #automation #smartfarming #agtech #robotics #ai #technology

Toradex OSM and Lino SoMs – 30×30mm NXP i.MX 93/i.MX 91 modules with solder-down or B2B connector designs

https://fed.brid.gy/r/https://www.cnx-software.com/2026/03/31/toradex-osm-and-lino-soms-30x30mm-nxp-i-mx-93-i-mx-91-modules-with-solder-down-or-b2b-connector-designs/

https://www.europesays.com/ie/405952/ Intel launches Core Ultra Series 3 AI gaming laptops #acer #ArtificialIntelligence(AI) #Asus #Australian #Cloud #Computers #ConsumerTech #ContentCreation #DataPrivacy #DataSecurity #deepseek #EdgeAI #EdgeComputing #Éire #EnergyEfficient #HP #IE #intel #Ireland #Laptops #LargeLanguageModels(LLMs) #Lenovo #MachineLearning(ML) #msi #NewZealand(NZ) #Nvidia #PCGaming #PCHardware #processors #SecurityOperationsCentres(SOCs) #semiconductors #SoutheastAsia #Technology

LooperRobotics Insight 9 standalone spatial AI camera features D-Robotics RDK X5 SoC, supports ROS 2 (Crowdfunding)

https://fed.brid.gy/r/https://www.cnx-software.com/2026/03/25/looperrobotics-insight-9-standalone-spatial-ai-camera-features-d-robotics-rdk-x5-soc-supports-ros-2/

Optimising edge AI hardware for industrial IoT deployments https://iottechnews.com/news/optimising-edge-ai-hardware-for-industrial-iot-deployments/ #edgeai #iiot #physicalai #edgecomputing #iot #ai #technology

Hugging Face’s Reachy Mini is an open-source AI robot for your computer or Raspberry Pi CM4

https://web.brid.gy/r/https://www.cnx-software.com/2026/03/24/hugging-face-reachy-mini-open-source-ai-robot-computer-raspberry-pi-cm4/