NVIDIA Hopper H100 & L4 Ada GPUs Achieve Record-Breaking Performance In MLPerf AI Benchmarks

[erek]

Impressive performance

"On the NVIDIA A30 GPU, which is a more affordable GPU, Deci delivered accelerated throughput and a 0.4% increase in F1 accuracy compared to an FP32 baseline.

By using Deci, teams that previously needed to run on an NVIDIA A100 GPU can now migrate their workloads to the NVIDIA A30 GPU and achieve 3x better performance than they previously had for roughly a third of the compute price. This means dramatically better performance for significantly less inference cloud cost."

Source: https://wccftech.com/nvidia-hopper-...breaking-performance-in-mlperf-ai-benchmarks/

 

[Axman]

Lol this thread's getting deleted.

 

[techie81]

Is this what people are considering tech news these days?

 

[GoldenTiger]

This belongs in soapbox, erek. You have access, you know the rules! .

EDIT: PS arstechnica isn't a tech site really nowadays, it has lots of political activism in its news.

 

[erek]

This belongs in soapbox, erek. You have access, you know the rules! .

EDIT: PS arstechnica isn't a tech site really nowadays, it has lots of political activism in its news.

Hmm, I see

 

[legcramp]

Someone from soapbox posted the job listing?

 

[GoldenTiger]

Someone from soapbox posted the job listing?

It's political, which is what the soapbox is for, not tech news which this is clearly not. https://hardforum.com/forums/soapbox.152/

 

[GoldenTiger]

Lol, erek completely replaced the OP instead of self locking... .