GPGPU

Successful Tape-Out of Loongson 3B6000 Processor

by
Successful Tape-Out of Loongson 3B6000 Processor

Recently, the Loongson 2K3000 (3B6000M) has completed preliminary functionality and performance assessments, with all indicators meeting expectations. The Loongson 2K3000 and Loongson 3B6000M are different packaging versions based on the same silicon wafer, targeting industrial control applications and mobile terminal fields, respectively.The chip integrates 8 LA364E processor cores, achieving a measured SPEC CPU 2006 Base … Read more

100% Self-Designed Architecture! Successful Tape-Out of the New Loongson CPU with Double Performance of the Second-Generation Self-Developed GPU

by
100% Self-Designed Architecture! Successful Tape-Out of the New Loongson CPU with Double Performance of the Second-Generation Self-Developed GPU

The official announcement from Loongson Technology states that recently, the Loongson 2K3000 and Loongson 3B6000M have successfully completed tape-out, and preliminary functionality and performance assessments have been completed, with all indicators meeting expectations. The Loongson 2K3000 and Loongson 3B6000M are different packaging versions based on the same silicon wafer, targeting the industrial control application field … Read more

100% Self-Developed Architecture! Longxin’s New Processor Successfully Taped Out, Performance Doubles

by
100% Self-Developed Architecture! Longxin's New Processor Successfully Taped Out, Performance Doubles

On April 3rd, Longxin Zhongke officially announced that the Longxin 2K3000 and 3B6000M chips have successfully completed tape-out. Longxin Zhongke stated that the 2K3000/3B6000M chips have completed preliminary functionality and performance assessments, with all indicators meeting expectations, targeting industrial control applications and mobile terminal fields respectively. It is reported that although the two chips are … Read more

Differences Between DPU and GPU

by
Differences Between DPU and GPU

(Source: techspot) Today, hardware and software applications for artificial intelligence have evolved into systems designed specifically to optimize AI and neural network operations. This includes Neural Processing Units (NPU), whose capabilities in accelerating AI tasks are often comparable to those of Graphics Processing Units (GPU). NPUs are increasingly common hardware designed to execute cutting-edge AI/machine … Read more

Experience AI Applications with the World’s First NPU+GPU+CPU Integrated AI Accelerator – Ryzen 7 8700G

by
Experience AI Applications with the World's First NPU+GPU+CPU Integrated AI Accelerator - Ryzen 7 8700G

AMD recently launched the world’s first desktop AI processor: the Ryzen 8000G series, marking the official entry of desktop PCs into the AI era. The Ryzen 8000G has garnered widespread attention from gamers and is selling hotly, poised to become the next generation’s blockbuster CPU. So, how powerful is the AI functionality of the Ryzen … Read more

Who Is the Main Character of the AI PC: CPU, GPU, or NPU?

by
Who Is the Main Character of the AI PC: CPU, GPU, or NPU?

As we all know, the “AI PC” has become one of the hottest topics in the consumer electronics industry today. For consumers who may not be well-versed in technical details but are intrigued by this concept, they believe that the “AI PC” can assist them in completing tasks they are not skilled at or alleviate … Read more

Efficient Point Cloud Inference with TorchSparse

by
Efficient Point Cloud Inference with TorchSparse

Click the card below to follow the “LiteAI” public account Hi, everyone, I am Lite. Some time ago, I shared the Efficient Large Model Full-Stack Technology from Part One to Nineteen, which includes topics such as large model quantization and fine-tuning, efficient inference for LLMs, quantum computing, and generative AI acceleration. The content links are … Read more

Unveiling the Secrets Behind Mobile Chips

by
Unveiling the Secrets Behind Mobile Chips

On September 10, Apple and Huawei held their product launch events simultaneously, inviting scrutiny from the market. The two tech giants—Huawei and Apple—unexpectedly chose this day to unveil their new products, undoubtedly bringing double anticipation to tech enthusiasts. This face-off has been humorously dubbed by many netizens as “mutual face-to-face grand opening”. So, when we … Read more

Understanding GPU Memory Usage in Large Models (Single GPU)

by
Understanding GPU Memory Usage in Large Models (Single GPU)

MLNLP community is a well-known machine learning and natural language processing community, with an audience covering NLP master’s and doctoral students, university professors, and corporate researchers. The vision of the community is to promote communication and progress between the academic and industrial sectors of natural language processing and machine learning, especially for beginners. Reprinted from … Read more

Single-GPU Operation for Thousands of Large Models: UC Berkeley’s S-LoRA Method

by
Single-GPU Operation for Thousands of Large Models: UC Berkeley's S-LoRA Method

Originally from PaperWeekly Author: Dan Jiang Affiliation: National University of Singapore Generally speaking, the deployment of large language models follows the “pre-training – then fine-tuning” model. However, when fine-tuning a base model for numerous tasks (such as personalized assistants), the training and service costs can become very high. Low-Rank Adaptation (LoRA) is a parameter-efficient fine-tuning … Read more