[WhitneyLand]

I am not buying this at all. But I’m not a hardware guy so maybe someone can help with why this is not true:

- Crypto hardware needed SHA256 which is basically tons of bitwise operations. That’s way simpler than the tons of matrix ops transformers need.

- NVidia wasn’t focused on crypto acceleration as a core competency. There are focussed on this, and are already years down the path.

- One of the biggest bottlenecks is memory bandwidth. That is also not cheap or simple to do.

- Say they do have a great design. What process are they going to build it on? There are some big customers out there waiting for TMSC space already.

Maybe they have IP and it’s more of a patent play.

(I mention crypto only as an example of custom hardware competing with a GPU)

[treesciencebot]

> One of the biggest bottlenecks is memory bandwidth. That is also not cheap or simple to do.

This is precisely why people are trying to put logic into memory instead of just making the logic chips simpler. Compute being 10x faster doesn't mean much when you want real-time, near-zero latency in the current day (and potentially, future) ML workloads. Memory bandwith for low batches are much more important, and even though this chip comes with HBM3E (which is cutting edge), that by itself won't make this faster than H200/MI300X.

[zaptrem]

Iirc Ethereum ASICs were also memory bandwidth bound. With KV caching transformers are just lots and lots of matrix vector multiplication and are bound by loading the huge weight matrices onto the cores.

[smugma]

https://www.eetimes.com/harvard-dropouts-raise-5-million-for...

“Uberti cites bitcoin mining chips as an example of a successful specialized ASIC offering.“

The founder also references crypto, so your comparison is an apt rebuttal to an argument you didn’t know they were making.

Overall, the article gives a small bit of detail, which is infinitely more than gleaned from the website.

[wokwokwok]

You are not the only one who is skeptical.

Nvidia has devoted an astronomical amount of effort to supporting AI as their “next big thing”.

…and here is some information-free landing page showing perf which is an order of magnitude above what nvidia is offering.

…but no numbers. You can get called out for numbers.

A vague infographic is much safer.

When things seem to good to be true, they usually are.

I guess some custom hardware with some cherry picked metric here, but frankly the whole thing screams scam.

If it was that easy, Amazon, Google, etc would have already done it with their proven ability to make new silicon.