M5Stack AI Acceleration Module LLM-8850 Brings 24 TOPS NPU to Raspberry Pi 5
https://www.electronics-lab.com/m5stack-ai-acceleration-module-llm-8850-brings-24-tops-npu-to-raspberry-pi-5/
The LLM-8850 module enhances edge systems with strong INT8 AI processing, multi-channel 8K video handling, and efficient cooling for stable high-load operation.
Memory Fabric System Tackles AI Inference’s Memory Bandwidth Challenges
https://www.electronics-lab.com/memory-fabric-system-tackles-ai-inferences-memory-bandwidth-challenges/
Enfabrica's new EMFASYS system integrates CXL-based DDR5 memory with RDMA Ethernet to reduce inference costs for large-scale AI workloads through an elastic memory fabric.
M5Stack Module LLM Kit – Offline AI Inference and Voice Assistant Module with Ethernet and USB Debugging
https://www.electronics-lab.com/m5stack-module-llm-kit-offline-ai-inference-and-voice-assistant-module-with-ethernet-and-usb-debugging/
M5Stack has introduced the Module LLM Kit, a smart modular solution designed for offline AI inference and data communication in various applications, such as smart home devices, voice assistants, and industrial control systems. It integrates the Module LLM and Module 13.2 LLM Mate modules to provide efficient and intelligent interaction without relying on the cloud, […]
Phison aiDAPTIV+: Hybrid AI Solution Combines SSD Caching and GPUs for Training Large Language Models
https://www.electronics-lab.com/phison-aidaptiv-hybrid-ai-solution-combines-ssd-caching-and-gpus-for-training-large-language-models/
Phison has recently showcased its aiDAPTIV+, a hybrid hardware and software solution designed to make large-language model (LLM) training more cost-effective and accessible, leveraging NAND flash technology to enhance efficiency. AI workstations and servers use it to support models like Llama, Falcon, Whisper, and ResNet. The Hybrid AI hardware solution allows small and medium-sized businesses […]
M5Stack Module LLM: AX630C SoC with 3.2 TOPs NPU for Offline AI Applications
https://www.electronics-lab.com/m5stack-module-llm-ax630c-soc-with-3-2-tops-npu-for-offline-ai-applications/
M5Stack’s Module LLM is an offline Large Language Model (LLM) inference module powered by the AX630C SoC, designed for terminal devices in smart homes, voice assistants, and industrial control systems. It enables local AI processing without relying on cloud services, enhancing privacy and providing reliable standalone operation. The AX630C SoC integrates a 3.2 TOPs NPU […]
Useful Sensors release AI in a Box– Run LLM locally with no internet connection
https://www.electronics-lab.com/useful-sensors-release-ai-in-a-box-run-llm-locally-with-no-internet-connection/
The founders of TensorFlow, a free and open-source software library for machine learning and artificial intelligence, launched a company– Useful Sensors. The company has released a crowdfunding project called AI in a Box, designed to provide users with their own private and offline AI system for various applications, such as conversation, live captions, translation, and […]
Amazon improves user experience of controlling smart homes with Alexa
https://www.electronics-lab.com/amazon-improves-user-experience-of-controlling-smart-homes-with-alexa/
Amazon highlights the challenges with your current interaction with Alexa. It believes that even though Alexa has improved the way people control their smart homes, there are still challenges. Users often have to remember specific phrases or device names, make multiple requests, or even repeat themselves when interacting with Alexa. Amazon recognizes the need to […]