Tagged articles
5 articles
Page 1 of 1
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Mar 3, 2026 · Artificial Intelligence

Can ROM‑Based LLM Accelerators Reach 20,000 tokens/s and End the GPU Era?

The article analyzes the ROMA and TOM architectures that embed large‑language‑model weights in on‑chip ROM + SRAM, achieving up to 20,000 tokens/s inference speed, compares them with GPU and Taalas solutions, and discusses their impact on edge AI, embodied intelligence, extreme environments, and privacy.

AI acceleratorEdge ComputingLLM
0 likes · 11 min read
Can ROM‑Based LLM Accelerators Reach 20,000 tokens/s and End the GPU Era?
OPPO Kernel Craftsman
OPPO Kernel Craftsman
Dec 22, 2023 · Fundamentals

Overview of Embedded ROM Flashing Processes and Online Programming Techniques

The article explains embedded ROM updating terminology, compares factory‑level burner programming with board‑level online flashing, details the boot sequence and U‑Boot implementation, outlines security signatures, common USB‑related issues, and the evolution of flash storage, concluding that online flashing offers low‑cost, scalable, high‑speed production for smartphones.

FlashingMobile DevelopmentROM
0 likes · 15 min read
Overview of Embedded ROM Flashing Processes and Online Programming Techniques
Baidu Intelligent Testing
Baidu Intelligent Testing
Sep 8, 2017 · Mobile Development

Android OEM ROM Features and Their Impact on App Testing

This article provides a comprehensive overview of the distinctive Android ROM customizations from major Chinese manufacturers—Huawei, OPPO, VIVO, Xiaomi, and Meizu—as well as key changes in Android versions 4.0 to 7.0, explaining how each feature affects app compatibility, permission handling, power management, and testing strategies.

AndroidMobileOEM
0 likes · 16 min read
Android OEM ROM Features and Their Impact on App Testing