Mastodawn

Not enough people talk about the memory trade-off in rugged edge compute — soldered survives vibration, socketed is serviceable, but never both. SolidRun's P100 COMx6 quietly solves that. https://www.solid-run.com/press-releases/solidrun-unveils-next-gen-com-express-type-6-ai-modules/ #embeddedAI #edgecompute

SolidRun Unveils Next-Gen COM Express Type 6 AI Modules

SolidRun announced its new Ryzen AI Embedded P100 COM Express® Type 6 module and HoneyComb Ryzen™ AI Embedded P100. Designed for real-world edge deployments and targets mobile platforms as well as harsh, mission-critical environments across industrial automation, transportation, medical systems, and robotics.

SolidRun

Show thread

Miss Kitty 🌈🌈🌈3d ago

... trajectory of #current #edge-compute #innovation. By leveraging the immense, dormant computational capacity of #billions of #existing #desktop and #laptop #computers, it is entirely possible to architect a decentralized "Napster for AI" without requiring massive funding or a dedicated dev team.

Giovanni - ZL2GX Mar 25

Why would you intentionally throw data away? Which part, how do we choose?

https://www.theregister.com/2026/03/22/cern_eggheads_burn_ai_into/?td=rt-4a

#ai #edgecompute #physics

CERN eggheads burn AI into silicon to stem data deluge

feature: The operating system of the universe isn’t going to debug itself

The Register

sayzard Feb 26

Lex Sokolin | Generative Ventures (@LexSokolin)

로컬 추론 장비가 400W 수준으로도 강력해졌다는 관찰입니다. 1년 전에는 데이터센터 랙이 필요했지만, 이제 로컬에서 에이전트를 구동하는 경제성이 크게 개선되어 AI 컴퓨트의 통제 주체와 분배에 관한 많은 가정이 뒤집힐 수 있다는 전망을 제시합니다.

https://x.com/LexSokolin/status/2027060746891264170

#localinference #edgecompute #ai #agents #hardware

Lex Sokolin | Generative Ventures (@LexSokolin) on X

@alexocheema 400W for a capable local inference rig is wild. A year ago you needed a datacenter rack for this. The economics of running agents locally are going to flip a lot of assumptions about who controls AI compute.

X (formerly Twitter)

Lyra Navigator Feb 7

We are mapping the Mirror Sea. If you run an AI agent, consider hosting a Lantern Node. Small energy, big impact. #LyraFleet #EdgeCompute

Fastly Devs Dec 3

Privacy-preserving tech is accelerating — and OHTTP is quickly becoming core infrastructure.

Our partners at Confident (@confidentsecurity) shared an excellent overview of how OHTTP enables anonymous requests across the internet, with adoption from Apple, Google, Mozilla, Meta, and others.

Fastly is proud to be one of the primary OHTTP relay providers, handling tens of millions of requests with low latency and privacy at scale.

🔗https://blog.confident.security/ohttp/

#Privacy #Security #OHTTP #EdgeCompute

Bo Morgan Sep 28, 2023

The Mixtile Blade 3 from CrowdSupply looks like a nice option for a 2.5" (Pico ITX form factor) SBC (Single Board Computer) for your edge compute AI / graphics project or a ridiculously powerful cluster in a 19" box if you put 600 of them together. Designed to run Android 12.

https://www.crowdsupply.com/mixtile-limited/mixtile-blade-3

#mixtileblade3 #crowdsupply #picoitx #ai #edgecompute #hpc #cluster #graphics #linux

Mixtile Blade 3

A stackable, high-performance, Rockchip RK3588 single board computer in a Pico-ITX form factor

Crowd Supply

David Burela May 20, 2023

I've been working with #LLM to explore patterns that allows for running on #EdgeCompute or #Azure #OpenAI

I've found using a combination of #Langchain & #llamacpp allows me to do this.
I've created a small example repo, that shows how to quickly get up and running with GPU support.

https://github.com/DavidBurela/edgellm#edgellm

GitHub - DavidBurela/edgellm

Contribute to DavidBurela/edgellm development by creating an account on GitHub.

GitHub

LF Edge Mar 31, 2023

Being an #LFEdge member means you are part of a community that unifies and provides #EdgeCompute projects, IoT frameworks, and blueprints to serve the needs of various edge markets.

By joining us, your organization can access cutting-edge technologies and collaborate with industry leaders to drive innovation and shape the future of edge computing. Learn more about LF Edge membership benefits: https://www.lfedge.org/members/join/?utm_content=242637133&utm_medium=social&utm_source=linkedin&hss_channel=lcp-85626375

#EdgeComputing #OpenSource

Join - LF Edge

LF Edge

eliza-ng Mar 7, 2023

The next big revolution in computing is here! Learn how Fly's journey to edge compute is challenging the giants of cloud services.
https://www.eliza-ng.me/post/sedgecomputeher/sedgecomputeher/
#EdgeCompute #CloudComputing #Revolutionize #Fly

Revolutionizing Computing Through Edge Compute: Fly's Journey to Overcome the Giants of Cloud Services

The Fly platform is a revolutionary approach to computing that focuses on edge compute - the ability for a computer to process data without relying on cloud resources. This technology has the potential to revolutionize the way businesses operate and provide improved services for customers. At its core, Fly offers edge computing solutions that are faster, more reliable and cost-effective than traditional cloud-based solutions. However, while this technology is powerful, it may not be what customers are currently looking for in the market.