News

New Technology ButterflyQuant Achieves 2-Bit Quantization, Promoting the Application of Large Language Models on Low-Power Devices

The core of ButterflyQuant lies in its learning capability, employing a learnable quantization method based on butterfly transformations. This technology draws inspiration from butterfly decomposition ...
Semiconductor Engineering

Neural Network Model Quantization On Mobile

The general definition of quantization states that it is the process of mapping continuous infinite values to a smaller set of discrete finite values. In this blog, we will talk about quantization in ...

Cambricon's Neural Network Model Quantization Training Method Patent Authorized

On September 15, People's Financial News reported that according to the Qichacha app, recently, Cambricon's wholly-owned subsidiary, Anhui Cambricon Information Technology Co., Ltd., was granted a ...

I ran a real AI chatbot locally on my iPhone — here’s how it worked

I tested running AI models locally on iPhone. Here’s how it works, why it’s free, and the surprising benefits of keeping ...
GIGAZINE

Dynamic quantization model that reduces the size of DeepSeek-R1 by up to 80% is now available

DeepSeek-R1, released by a Chinese AI company, has the same performance as OpenAI's inference model o1, but its model data is open source. Unsloth, an AI development team run by two brothers, Daniel ...
JCN Newswire

Fujitsu develops generative AI reconstruction technology for optimized and energy-efficient AI models based on Takane LLM

Kawasaki, Japan, September 8, 2025 - (JCN Newswire) - Fujitsu today announced the development of a new reconstruction ...
EDN

Managing noise in the signal chain, Part 2: Noise and distortion in data converters

The sources of noise in a signal chain can be either internal or external. Managing noise in the signal chain requires meticulous examination of each circuit in the chain to minimize noise where ...
Electronic Design

Behind the ADC Veil: Demystifying Common DC Specifications (.PDF Download)

As its name implies, the function of an analog-to-digital converter (ADC) is to convert analog signals to digital representations for processing by a microcontroller (MCU), field-programmable gate ...