Nvidia wins MLPerf once again, by a mile. But AMD demonstrated it can compete with the older H200 in training smaller models.

F or those who enjoy rooting for the underdog, the latest MLPerf benchmark results will disappoint: Nvidia’s GPUs have ...

And that’s where Nvidia excels. Finally, I can stop whining about AMD’s lack of open AI benchmarks. AMD has published excellent MLPerf inference results for their MI300 GPU, which is ...

AMD has finally published its first official MLPerf results for the Instinct MI300X accelerator for AI and HPC. The MI300X processor apparently performs in line with Nvidia's previous-generation ...

NVIDIA, Oracle, Quanta Cloud Technology, SCITIX, Supermicro, and TinyCorp. “We would especially like to welcome first-time MLPerf Training submitters AMD, IBM, MangoBoost, Nebius, and SCITIX ...

Nvidia always excels at each of the newest rounds of MLPerf benchmarks and the latest result is another entry into the ...

Based on the progress that Nvidia, among others, has successively made in the MLPerf results, this can certainly be made up for. Exciting: AMD also submitted a configuration with only one MI300X ...

Using 32 AMD Instinct™ MI300X GPUs across four nodes, MangoBoost fine-tuned the Llama2-70B-LoRA model in just 10.91 minutes, setting the fastest multi-node MLPerf benchmark on AMD GPUs to date. The ...

The low market share in the AI segment will also give AMD a longer growth runway compared to Nvidia as companies look for cheaper alternatives. The latest MLPerf Inference test results have been ...

We finally have the first benchmarks from MLCommons, the vendor-led testing organization that has put together the suite of MLPerf AI training and inference benchmarks, that pit the AMD Instinct ...

The company’s recent MLPerf Training v5.0 submission, which utilized 2,496 NVIDIA Blackwell GPUs, is the largest of its kind to date and marks a significant advance in AI workload capabilities ...

This milestone marks the first-ever multi-node MLPerf inference ... the server scenario on AMD MI300X GPUs, outperforming the previous best result of 82,749 TPS on NVIDIA H100 GPUs.