Categories
Featured

¿Muy poco y demasiado tarde? Bertha LPU se une a la LPU ultrarrápida de Groq a medida que crece el desafío al gigante de GPU de Nvidia

[ad_1]

Una startup de inteligencia artificial en Corea del Sur Hiper Axel Se asoció con la empresa de SoC basada en plataforma y el diseñador de ASIC SEMIFIVE en enero de 2024 para desarrollar Bertha LPU.

Diseñado para la inferencia LLM, Bertha ofrece “bajo costo, baja latencia y características específicas de dominio”, con el objetivo de reemplazar las GPU de “alto costo y baja eficiencia”. SEMIFIVE informa que el trabajo ya se ha completado y que el procesador, diseñado con tecnología de 4 nm, se producirá en masa a principios de 2026.

[ad_2]

Source Article Link

Categories
Featured

This startup wants to take on Nvidia with a server-on-a-chip to eliminate what it calls an already flawed system — faster GPU, CPU, LPU, TPU or NIC will not deliver the leap that many firms are aiming for

[ad_1]

According to Israeli startup NeuReality, many AI possibilities aren’t fully realized due to the cost and complexity of building and scaling AI systems. 

Current solutions are not optimized for inference and rely on general-purpose CPUs, which were not designed for AI. Moreover, CPU-centric architectures necessitate multiple hardware components, resulting in underutilized Deep Learning Accelerators (DLAs) due to CPU bottlenecks.

[ad_2]

Source Article Link

Categories
News

Groq LPU (Language Processing Unit) performance tested – capable of 500 tokens per second

 Groq LPU Inference Engine performance tested

A new player has entered the field of artificial intelligence in the form of the Groq LPU (Language Processing Unit). Groq has the remarkable ability to process over 500 tokens per second using the Llama 7B model.  The Groq Language Processing Unit (LPU), is powered by a chip that’s been meticulously crafted to perform swift inference tasks. These tasks are crucial for large language models that require a sequential approach, setting the Groq LPU apart from traditional GPUs and CPUs, which are more commonly associated with model training.

The Groq LPU boasts an impressive 230 on-die SRAM per chip and an extraordinary memory bandwidth that reaches up to 8 terabytes per second. This technical prowess addresses two of the most critical challenges in AI processing: compute density and memory bandwidth. As a result, the Groq LPU Groq LPU (Language Processing Unit). Its development team describe it as a “Purpose-built for inference performance and precision, all in a simple, efficient design​.”

Groq LPU Performance Analysis

But the Groq API’s strengths don’t stop there. It also shines in real-time speech-to-speech applications. By pairing the Groq with Faster Whisperer for transcription and a local text-to-speech model, the technology has shown promising results in enhancing the fluidity and naturalness of AI interactions. This advancement is particularly exciting for applications that require real-time processing, such as virtual assistants and automated customer service tools.

Here are some other articles you may find of interest on the subject of Language Processing Units and AI :

A key measure of performance in AI processing is token processing speed, and the Groq has proven itself in this area. When compared to other models like ChatGPT and various local models, the Groq API demonstrated its potential to significantly impact how we engage with AI tasks. This was evident in a unique evaluation known as the chain prompting test, where the Groq was tasked with condensing lengthy texts into more concise versions. The test not only showcased the API’s incredible speed but also its ability to handle complex text processing tasks with remarkable efficiency.

It’s essential to understand that the Groq LPU is not designed for model training. Instead, it has carved out its own niche in the inference market, providing a specialized solution for those in need of rapid inference capabilities. This strategic focus allows the Groq LPU to offer something different from Nvidia’s training-focused technology.

The tests conducted with the Groq give us a glimpse into the future of AI processing. With its emphasis on speed and efficiency, the Groq LPU is set to become a vital tool for developers and businesses that are looking to leverage real-time AI tasks. This is especially relevant as the demand for real-time AI solutions continues to grow.

For those who are eager to explore the technical details of the Groq API, the scripts used in the tests are available through a channel membership. This membership also provides access to a community GitHub and Discord, creating an ideal environment for ongoing exploration and discussion among tech enthusiasts.

The Groq represents a significant step forward in the realm of AI processing. Its ability to perform rapid inference with high efficiency makes it an important addition to the ever-evolving landscape of AI technologies. As the need for real-time AI solutions becomes more pressing, the specialized design of the Groq LPU ensures that it will play a key role in meeting these new challenges.

Filed Under: Technology News, Top News





Latest timeswonderful Deals

Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, timeswonderful may earn an affiliate commission. Learn about our Disclosure Policy.