Articles

13 articles
Tag: edge ai ✕
CVPR 2026: Mutual Pair Merging Cuts Vision Transformer Latency 60% on Raspberry Pi 5 ML
2026-04-08T09:59:48.737Z · Src: 2026-04-08T00:00:00.000Z
vision transformertoken mergingcvpr 2026
ID-Selection: Prune 97% of Visual Tokens in Vision-Language Models While Keeping 92% of Performance ML
2026-04-08T09:19:42.499Z · Src: 2026-04-08T00:00:00.000Z
lvlmvision languageefficiency
Small Language Models Can Match LLMs as Search Agents With Proper Training, Study Shows AI
2026-04-07T22:47:04.578Z · Src: 2026-04-07T00:00:00.000Z
small language modelsearch agentsslm
MUXQ: New Quantization Method Solves LLM Activation Outlier Problem for NPU Deployment AI
2026-04-07T19:54:14.181Z · Src: 2026-04-07T00:00:00.000Z
llmquantizationnpu
Google Launches Free Offline AI Dictation App That Auto-Polishes Your Speech Tech
2026-04-07T14:05:43.088Z · Src: 2026-04-07T00:00:00.000Z
googleaidictation
The Neuromorphic Computing Breakthrough: Brain-Inspired Chips That Could Outperform GPUs for AI Tech
2026-04-05T00:55:40.793Z · Src: 2026-04-04T00:00:00.000Z
neuromorphic computiintel loihiibm northpole
The Edge AI Inference Boom: Why Running Models Locally Is the Next Big Thing in Computing Tech
2026-04-05T00:54:38.072Z · Src: 2026-04-04T00:00:00.000Z
edge aiinferencenvidia jetson
The Edge AI Imperative: Why Running AI Models Locally Is Becoming Essential for Privacy and Latency AI
2026-04-04T19:55:52.247Z · Src: 2026-04-04T00:00:00.000Z
edge aion device aiapple intelligence
The Rise of Edge AI Inference: Why Running Models Locally Beats Cloud APIs for Many Use Cases Tech
2026-04-04T18:55:13.444Z · Src: 2026-04-04T00:00:00.000Z
edge aiapplenvidia jetson
PrismML Bonsai 8B: Caltech Venture Releases 1-Bit Quantized LLM That Runs on a Laptop AI
2026-04-04T16:23:25.819Z · Src: 2026-04-04T00:00:00.000Z
llm1 bitquantization
PrismML Unveils 1-bit Bonsai 8B LLM: 14x Smaller, 8x Faster, 5x More Energy Efficient AI
2026-04-04T14:14:16.524Z · Src: 2026-04-04T00:00:00.000Z
llm1 bitquantization
AMD Lemonade：支持 GPU 和 NPU 的开源本地 AI 服务器 AI
2026-04-03T03:04:59.000Z · ★ 80
# AMD Lemonade：支持 GPU 和 NPU 的开源本地 AI 服务器 AMD 发布了 **Lemonade**——一个快速、开源的本地 AI 服务器，可在 GPU 和 NPU 上运行，使开发者和用户能够在自己的硬件上私密运行多个 AI 模型。 ## 什么是 Lemonade？ Lemonade 是一个轻量级、本地优先的 AI 服务器，为多种 AI 模态提供统一 API： - *
amdlemonadelocal ai
AMD Lemonade: Open Source Local AI Server for Text, Images, and Speech AI
2026-04-03T03:04:56.000Z · ★ 80
# AMD Lemonade: Open Source Local AI Server for Text, Images, and Speech AMD has released **Lemonade**, a fast, open source local AI server that runs on both GPUs and NPUs, enabling developers and us
amdlemonadelocal ai