395 annotations
Page 6 of 20
H200 increases it by another factor of 2.
(No comment added)
Transcript
2024 Q3
2 Dec 23
TensorRT LLM on the same GPU, without anybody touching anything, improves the performance by a factor of 2.
And then on top of that, of course, the pace of our innovation is so high. H200 increases it by another factor of 2.
And so our inference performance, another way of saying inference cost, just reduced by a factor of 4 within about a year's time.
(No comment added)
Transcript
2024 Q3
2 Dec 23
I still get a lot of questions from investors
(No comment added)
Transcript
2024 Q3
2 Dec 23
I still get a lot of questions from investors
(No comment added)
Transcript
2024 Q3
2 Dec 23
as inference, even large model inference takes more and more of the TAM that the market will become more competitive
(No comment added)
Transcript
2024 Q3
2 Dec 23
We are still working on improving our supply and plan on continuing and growing all throughout next year
(No comment added)
Transcript
2024 Q3
2 Dec 23
So could our guidance have been a little higher in our Q4? Yes.
(No comment added)
Transcript
2024 Q3
2 Dec 23
are you supply constrained in just reshipping stuff that would have gone to China elsewhere?
(No comment added)
Transcript
2024 Q3
2 Dec 23
Our business model is basically a license.
(No comment added)
Transcript
2024 Q3
2 Dec 23
NVIDIA AI Enterprise is $4,500 per GP per year.
(No comment added)
Transcript
2024 Q3
2 Dec 23
We help them build their custom AI. We help them make that custom AI incredible.
Then that customer AI becomes theirs, and they deploy it on a run time that is enterprise grade, enterprise optimized or outperformance optimized, runs across everything NVIDIA.
(No comment added)
Transcript
2024 Q3
2 Dec 23
They can't afford to outsource their intelligence and hand out their data and hand out their flywheel for other companies to build the AI for them.
(No comment added)
Transcript
2024 Q3
2 Dec 23
There is a glaring opportunity in the world for AI foundry
(No comment added)
Transcript
2024 Q3
2 Dec 23
It weighs 70 pounds. Eight of the chips are Hopper.
(No comment added)
Transcript
2024 Q3
2 Dec 23
the HGX, H100, the Hopper HGX, has 35,000 parts
(No comment added)
Transcript
2024 Q3
2 Dec 23
We are expanding our supply quite significantly.
(No comment added)
Transcript
2024 Q3
2 Dec 23
Grace Hopper is in production in high-volume production now.
(No comment added)
Transcript
2024 Q3
2 Dec 23
We are on a very, very fast ramp with our first data center CPU to a multibillion-dollar product line.
(No comment added)
Transcript
2024 Q3
2 Dec 23
It adds to Ethernet with an end-to-end solution with BlueField as well as our Spectrum switch
(No comment added)
Transcript
2024 Q3
2 Dec 23
we invented this new platform that extends Ethernet
(No comment added)
Transcript
2024 Q3
2 Dec 23