Filter
Exclude
Time range
-
Minimum likes
We built an arcade cabinet from scratch. It runs Winnitron, Winnipeg's open-source indie arcade platform, plus a Jetson Nano computer vision pipeline that watches the players. bsdxr.com/projects/orwellotr… #IndieGames #EdgeAI
16
🚀 Starting SemNav, a semantic-aware autonomous navigation project. Building with ROS 2, Nav2, YOLO, OpenCV, 2D LiDAR, ONNX Runtime, C++, Gazebo & RViz2. Currently at the simulation + implementation stage. Building it step by step. 🤖 #Robotics #ROS2 #EdgeAI
1
1
41
🚨 AI is moving off Earth. India’s TakeMe2Space is set to launch MOI-1A, an orbital computing satellite using NVIDIA Orin NX processors to analyze data in orbit instead of sending raw data to Earth. Why it matters: edge AI may soon operate in space. #AI #EdgeAI #MLOps #SpaceTech
1
12
Go, Rust, Java for Android, Swift for iOS — a tour of every DefraDB SDK, plus why rolling your own GraphQL driver is surprisingly easy. Find out more: docs.source.network #Source #DefraDB #EdgeAI
3
3
131
Whistle packs 7-language speech recognition into 16.9 MB, with Apache-2.0 weights. Cactus's 11 ms first-token result used a 10-second clip on an M4 Pro CPU, not a microcontroller. For edge deployment, test latency on the actual device. #SpeechRecognition #EdgeAI
We release Whistle: speech to text in a 16.9MB file, running on the CPU in the same engine as Needle. It mostly beats Whisper base with 9x less file size and 6x speed. Whistle supports English, German, French, Spanish, Italian, Dutch and Polish. cactuscompute.com/blog/whist…
15
Edge computing quietly solved the problem cloud computing created — pushing intelligence back to the device instead of the data center. #EdgeAI #Tech
1
8
Qualcomm reveals its next-generation NPU architecture, targeting 100+ tokens per second for local generative workloads on next-gen laptops and automotive systems. ​#Qualcomm #Semiconductors #EdgeAI #Hardware #TechTrends
22
Meta releases an optimized Llama inference kernel designed specifically for low-power edge chips, slashing local memory overhead without degrading output coherence. ​#MetaAI #Llama #EdgeAI #OpenSource #MachineLearning
8
Very interesting! The next battleground for #AI is devices. We are likely to see proliferation of various #edgeAI devices in coming years to complement the agentic and software experience
🚨 MUSE ECOSYSTEM ALERT 🚨 today we are announcing Muse Gadgets! this is an open-source ESP32 firmware and Linux SDK for anyone to make hardware that works with Muse we are also releasing our own gadget—Muse Home Link—to enable your muse to work with your smart devices (TV, speakers, etc.)
9
@AMD is sampling its Versal AI Core XQRVC1902 adaptive SoC in a new space-grade package designed for missions lasting up to 15 years, targeting demanding onboard processing and AI workloads. #SpaceTech #EdgeAI #AdaptiveComputing edge-ai-vision.com/2026/10/a…
83
🎥 Missed our webinar? Beyond the GPU is now available on YouTube. Learn how PVA can offload vision workloads on NVIDIA Jetson, freeing GPU resources for AI inference. ▶️ Watch now: piped.video/watch?v=pCTXvmHt… #NVIDIAJetson #PVA #EdgeAI #RidgeRun
2
46
Apex Compute is developing a GPU with an open-source Vulkan driver built on Mesa, targeting shared graphics + AI processing for edge systems including robotics, drones and autonomous vehicles. #EdgeAI #GPU #Vulkan #OpenSource @apexcompute edge-ai-vision.com/2026/10/a…
84
NVIDIA's DGX Spark 64GB ships Oct 23 at $4,999 — 100B params on one desk. The 128GB FE is $6,950: +$1,951 (+39%) for double the memory, same GB10 chip. So the price ladder isn't compute. It's memory. Per-token billing meters a model's words, not its state. #EdgeAI
20
@Arm’s free Arm Create developer event lands in San Jose Oct. 19 with hands-on AI workflows, PyTorch + ExecuTorch, agentic AI, MCP, edge AI and physical AI sessions, demos and developer challenges. #EdgeAI #PhysicalAI #AgenticAI edge-ai-vision.com/2026/10/u…
76
🧠Sophia Space and Redwire are partnering to develop orbital data centers, combining Sophia’s edge-computing spacecraft with Redwire’s space infrastructure and manufacturing capabilities. Read more: satnow.com/news/details/5936… #edgeai #orbital #satellite #datacenter #space
27
Amazon and Cloudflare roll out ultra-lightweight open models enabling complex on-device reasoning across smartphones and low-cost local servers without continuous cloud connectivity. ​#EdgeAI #Cloudflare #OpenSource #OnDeviceAI #TechTrends
10
Processor selection for edge AI is about more than TOPS. @RetailNext's Mark Jamtgaard and @eetimes’ Sally Ward-Foxton dig into software maturity, data movement, thermal limits, quantization, OTA updates and TCO. #EdgeAI #ComputerVision @sallywf edge-ai-vision.com/2026/10/i…
1
2
169
AGVs follow guided routes; AMRs can navigate using sensors and mapping. When onboard vision or AI is needed, an edge computer can process sensor data locally. STS supplies industrial computing solutions across India. sales@sundartechno.com | +91-9482081014 #AGV #AMR #EdgeAI
1
1
15
AGVs follow guided routes; AMRs can navigate using sensors and mapping. When onboard vision or AI is needed, an edge computer can process sensor data locally. STS supplies industrial computing solutions across India. sales@sundartechno.com | +91-9482081014 #AGV #AMR #EdgeAI
1
1
18
@ST_World explores how imaging is evolving into machine perception—combining vision, depth sensing and AI-ready processing to turn light into trusted data for physical AI systems. #PhysicalAI #EdgeAI #ComputerVision #Sensors edge-ai-vision.com/2026/10/t…
84