Karl Freund

Lafayette

Founder and Principal Analyst at Cambrian-AI Research LLC

Contributor at Forbes

Founder and Principal Analyst, Cambrian-AI Research LLC

Featured in: Favicon

cambrian-ai.com

linkedin.com Favicon

forbes.com Favicon

eetimes.com Favicon

newsbreak.com Favicon

moorinsightsstrategy.com Favicon

beamstart.com Favicon

flipboard.com Favicon

businesspostexaminer.com Favicon

bfn.today + 2 more

Articles

Latest MLPerf Shows AMD Catching Up With Nvidia, Sort Of...

5 days ago | forbes.com | Karl Freund

Advanced Micro Devices (AMD) headquarters on in Santa Clara, California. Getty ImagesAs you AI pros know, the 125-member MLCommons organization alternates training and inference benchmarks every three months. This time around, its all about training, which remains the largest AI hardware market, although not by much as inference drives more growth as the industry shift from research (building) to production (using). As usual, Nvidia took home all the top honors.
Nvidia Takes Major Step To Leverage Its Rack-Scale Ecosystem

1 week ago | cambrian-ai.com | Karl Freund

While few dispute the incredible performance of Nvidia AI platforms, many complain that it is a closed system. You can’t replace the Arm CPUs with, say, a CPU from a RISC-V , or take advantage of a new AI ASIC like the Meta MTIA accelerator, without redesigning and building everything from scratch. The key to the gate of this walled garden is NVLink, which no non-Nvidia CPU or GPU/ASIC supports today. Thats about to change, with huge potential ramifications.
Nvidia Takes Major Step To Leverage Its Rack-Scale Ecosystem

2 weeks ago | forbes.com | Karl Freund

While few dispute the incredible performance of Nvidia AI platforms, many complain that it is a closed system. You can’t replace the Arm CPUs with, say, a CPU from a RISC-V , or take advantage of a new AI ASIC like the Meta MTIA accelerator, without redesigning and building everything from scratch. The key to the gate of this walled garden is NVLink, which no non-Nvidia CPU or GPU/ASIC supports today. Thats about to change, with huge potential ramifications.
Meta Enters The Token Business, Powered By Nvidia, Cerebras And Groq

2 weeks ago | cambrian-ai.com | Karl Freund

This is really a big deal for Meta and the AI industry as the maker of the popular open-source Llama LLM seeks to directly monetize the incredible adoption Meta has realized. Developers just access the model from the cloud; no hardware or software to install. But it is also a big deal for Cerebras and Groq, the two startups selected by Meta for serving fast tokens, many times faster than a GPU.
EDA Vendors Help Intel Get The USA Back Into Chip Manufacturing

2 weeks ago | cambrian-ai.com | Karl Freund

Intel is the primary (only) hope for revitalizing advanced domestic manufacturing in the USA, and the entire industry is anxiously awaiting adoption of Intel “18A” fabrication capability and solid proof of its performance.
Speeding AI With Co-Processors

2 weeks ago | cambrian-ai.com | Karl Freund

Most chips today are built from a combination of customized logic blocks that deliver some special sauce, and off-the-shelf blocks for commonplace technologies such as I/O, memory controllers, etc. But there is one needed function that has been missing; an AI co-processor. In AI, the special sauce has been the circuits that do the heavy-lifting of parallel matrix operations. However, other types of operations used in AI do not lend themselves well to such matrix and tensor operators and silicon.
Speeding AI With Co-Processors

1 month ago | forbes.com | Karl Freund

Most chips today are built from a combination of customized logic blocks that deliver some special sauce, and off-the-shelf blocks for commonplace technologies such as I/O, memory controllers, etc. But there is one needed function that has been missing; an AI Co-Processor. In AI, the special sauce has been the circuits that do the heavy-lifting of parallel matrix operations. However, other types of operations used in AI do not lend themselves well to such matrix and tensor operators and silicon.
EDA Vendors Help Intel Get The USA Back Into Chip Manufacturing

1 month ago | forbes.com | Karl Freund

The US Semiconductor industry desperately needs to rebuild the country’s ability to produce the advanced chips that are the cornerstone of AI and every electronic device you can imagine. Most of those chips are built today in Taiwan by TSMC. Merely the thought of any potential Chinese aggression in Taiwan sends shivers down the spines of industry, market, and government officials, and an outright attack would put the worldwide economy in a tailspin.
Meta Enters The Token Business, Powered By Nvidia, Cerebras And Groq

1 month ago | flipboard.com | Karl Freund

3 hours agoAt its inaugural LlamaCon AI developer conference on Tuesday, Meta announced an API for its Llama series of AI models: the Llama API. Available in limited preview, the Llama API lets developers explore and experiment with products powered by different Llama models, per Meta. Paired with Meta’s SDKs, …
Meta Enters The Token Business, Powered By Nvidia, Cerebras And Groq

1 month ago | forbes.com | Karl Freund

Meta held its first-ever event for AI developers, LlamaCon, at the company’s headquarters in Menlo Park, where it announced that it was ready to compete with ChatGPT from OpenAI, as well as Google, AWS, and AI-as-a-service startups. This is really a big deal for Meta and the AI industry as the maker of the popular open-source Llama LLM seeks to directly monetize the incredible adoption Meta has realized. Developers just access the model from the cloud; no hardware or software to install.