Why NVIDIA is Terrified of This New AI Chip

NVIDIA's dominance in the AI chip market might finally be challenged-and it's all thanks to Intel's new Gaudi® line. In this video, we dive into the capabilities of Gaudi® 2 and explore what makes it a formidable contender against NVIDIA's GPUs. We’re also looking into the future with Intel’s Gaudi® 3 and Xeon® 6 announcements. What does this mean for the AI chip landscape, and how will NVIDIA respond? Join me as we explore Intel's game-changing advancements and the potential shift they could bring to AI research and hardware diversity. Thank you Intel for sponsoring this video, I'm happy to be an Intel Ambassador. Leave a comment below and let me know your thoughts on Intel vs. NVIDIA!
Intel Dev Cloud:
www.intel.com/...
Intel on AWS:
aws.amazon.com...
Want more AI/ML education? Connect with me here:
X: x.com/sirajraval
Facebook: / sirajology
Linkedin: / sirajraval
TikTok: www.tiktok.com...
Instagram: / sirajraval
Build your own AI Trading bot for Stocks & Crypto (NO CODE!):
www.tradergpt.co
Can ChatGPT o1-Preview Make Me Money?:
• Can ChatGPT O1 Make Me...
I Built a Trading Bot with ChatGPT:
• I Built a Trading Bot ...
AI Turned $10K Into Profits (in 24 Hours):
• AI Turned $10k into Pr...
I Built a Sports Betting Bot with ChatGPT:
• I Built a Sports Betti...
Watch ChatGPT Build an AI Startup:
• Watch ChatGPT Build an...
Watch ChatGPT Build a Finance Startup:
• Watch ChatGPT Build a ...
Watch Me Build a Startup Playlist:
• Watch Me Build a Finan...
Build your own AI Trading bot for Stocks & Crypto (NO CODE!):
www.tradergpt.co
🔔 Subscribe and hit the notification bell to join the AI revolution! www.wagergpt.xyz

[@Voidroamer]

hey, you are still alive! neat to see you around :)

[@epokaixyz]

Consider this your cheat sheet for applying the video's advice: 1. Explore Intel's Gaudi® offerings for faster and cheaper AI model training. 2. Support companies like Intel that promote open ecosystems and avoid vendor lock-in. 3. Consider the versatility of AI hardware like Gaudi® and its ability to handle diverse workloads. 4. Get hands-on experience with Gaudi® through cloud-based solutions like AWS.

[@frankbraker1320]

"I gotta train my AI model." After hitting the stop recording button on his camera, he goes to the other room to sit down with his baby AI and do exercises. What a good father! :)

[@dcity-b4u]

As a tech geek, I also see value in this as an investment advice, it's on you Siraj if this stock doesn't peak 😂

[@abhayranade5815]

Nice video sir,one question,is any dedicated sdk available to access amd or intel core ultra NPU?

[@samiloom8565]

Your videos are still very good

[@12_MPH_400_metres]

i am most mad about TSMC [Taiwan Semiconductor] has probably been getting subsidy from Taiwan for so many years. now TSMC is getting subsidy from the U.S.A. too.

[@TheHolyEagle33]

whats your stance on analog chips? stochastic computing may be the future of computers.

[@SirajRaval]

im not as bullish on them but ill do some more research. biological computing would be cool too

[@TheHolyEagle33]

@@SirajRaval analog computers and quantum analog computers are popular terms.

[@levelup89204]

is crazy how people are sleeping on intel

[@leonardoruiz5994]

You are right

[@taxcle7267]

Nobody was sleeping on intel. We just hope for more competition.

[@sndrstpnv8419]

can you share python code from video?

[@Met1900]

Can it run crysis on 1080p?

[@SirajRaval]

yes

[@yuvrajkukreja9727]

yay ! more cheeper ai hardware that breaks the nvedia monopaly !

[@ypey1]

Just bought my intel stock

[@ps3301]

If people have to pick the ultimate ai chip, Cerebras is better. Gaudi uses hdm that is always slower than sram.

[@SirajRaval]

i need to look into cerebras thanks

[@chinesesparrows]

Cerebras looks to be a binning and maintenance nightmare. Except for specialist needs more smaller more modular systems appear to be easier to operate, maintain and scale.

[@Kanze-f3y]

Very Sad. Mps wakijadili mtu mambo mhumu ya kusaidia Hawa imeachwa.

[@mvasa2582]

HBM2e and PCIe5 are still behind Nvidia. NVLink is far superior when you construct a large number of clusters. Intel has much more to prove for large-scale 80-100 billion parameter > 8K GPU-sized clusters. Infiniband may not be open standards - but it is far superior. We also have SpectrumX for Ethernet compatibility. Infiniband will play a crucial role in Blackwell when you are guaranteed 800Gbps between nodes or between all 36 GPUs in a Rack. Yes, this is by far a great option for training and probably the best price performance. We need to see more performance benchmarks. I would also love to hear about how you got your workload distribution and potentially CPU saturation working (if you did).

[@SirajRaval]

Sounds like you have a lot of experience, thanks for sharing. More benchmarks are coming soon, glad to see competition in this space

[@rousabout7578]

Pointless comparing the latest Intel chip with NVIDIAs previous generation chip. How does it compare to the new NVIDIA Blackwell chip?

[@BrutalStrike2]

I bet Intel uploading fake benchmarks as usual 😅

[@YouWillDoAsYouAreTold]

yeah 😂nvidia is definetly not scared

[@leonardoruiz5994]

You think that There are lawyers you know, if there claims are faked they would not go without problems Perhaps you just hate Intel

[@Betelgeusephotography]

As nvidia just says it's faster with no numbers

[@blueberryclash8893]

intel not recalling their faulty chips they might go bankrupt

[@covenant1231]

This guy is clueless