Elim Kwan

icon indicating a website link https://elimkwan.github.io/

icon location Research Engineer at the Alan Turing Institute | MPhil Advanced CS at the University of Cambridge | MEng at the University of Bristol

Results 1 issues of Elim Kwan

FMHA error when reproducing DELL BERT benchmark

10 comment

We tried to follow the [Dell example](https://github.com/mlcommons/training_results_v1.1/tree/main/Dell/benchmarks/bert/implementations/pytorch) to reproduce the Bert Training Benchmark on a server with 2 GPUs. We have encountered an error when running the model encoder layer,...